论文库

检索计算机领域论文，按研究方向、作者或关键词筛选。

部分采集异常

正在读取账号与研究记录…

全站更新概况

+0新增论文

+0其中 AI 相关

+0已有论文修订

+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 07:38 — 2026-11-16 07:38（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 23,348 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6504c614b58c48bf5697bc272c9dc07CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation

Zhang, Jiangning, Zhu, Junwei, Gan, Zhenye, Luo, Donghao, Lin, Chuming, Xu, FeiFan, Peng, Xu, Hu, Jianlong 等 17 位作者

原文摘要

We propose a multimodal-driven framework for high-fidelity long-term digital human animation termed Soul, which generates semantically coherent videos from a single-frame portrait image, text prompts, and audio, achieving precise lip synchronization, vivid facial expressions, and robust identity preservation. We construct Soul-1M, containing 1 million finely annotated samples with a precise automated annotation pipeline (covering portrait, upper-body, full-body, and multi-person scenes) to mitigate data scarcity, and we carefully curate Soul-Bench for comprehensive and fair evaluation of audio-/text-guided animation methods. The model is built on the Wan2.2-5B backbone, integrating audio-injection layers and multiple training strategies together with threshold-aware codebook replacement to ensure long-term generation consistency. Meanwhile, step/CFG distillation and a lightweight VAE are used to optimize inference efficiency, achieving an 11.4xspeedup with negligible quality loss. Extensive experiments show that Soul significantly outperforms current leading open-source and commercial models on video quality, video-text alignment, identity preservation, and lip-synchronization accuracy, demonstrating broad applicability in real-world scenarios such as virtual anchors and film production.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b659a8670c22ce00cb9311c6cde8dd8eCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Jailbreaking Vision-Language Models via Dissonance-Guided Suffix Optimization and Image-Phrase Injection

Pi, Jiacheng, Yang, Zhiguo, Huang, Xingxing, Xu, Dongsheng, Zhong, Ruizhi, Ruan, Wenjie

原文摘要

The integration of vision and language in Vision-Language Models (VLMs), while enabling multimodal capabilities, inherently expands their attack surface. Among existing white-box jailbreak methods, suffix-optimization-based approaches often rely on gradient approximations over discrete token spaces, yielding insufficient guidance and causing optimization to stagnate in local optima, while image-perturbation-based ones frequently exhibit poor cross-model transferability. In this work, we introduce DGSIP, a Dissonance-Guided Suffix Optimization and Image-Phrase Injection framework. DGSIP leverages predictive dissonance between the target model and an unaligned model to identify tokens suppressed by safety alignment, using them as a more effective signal than gradient-based cues for suffix optimization. It further reinforces the attack by jointly optimizing the content and presentation of phrase embedded in images to leverage VLMs' cross-modal sensitivity. Our extensive experiments demonstrate that DGSIP outperforms prior baselines across multiple safety benchmarks and a range of open-source VLMs (e.g., MiniGPT-4, InstructBlip and LLaVA). Notably, compared to baselines, our method exhibits much stronger transferability to commercial black-box VLMs, such as GPT-4o-Mini, Gemini 2.0 Flash and Qwen 2.5-VL. Based upon DGSIP, we empirically reveal critical vulnerabilities in the safeguard mechanisms of current VLMs, highlighting the need for more robust defense strategies. The implementation is available on https://github.com/Trusted-LLM/DGSIP.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b65d6730199d6dc2e915f799250ba286CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Liu, Mingyu, Shu, Jiuhe, Chen, Hui, Li, Zeju, Zhao, Canyu, Yang, Jiange, Gao, Shenyuan, Chen, Hao 等 9 位作者

原文摘要

A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and decision making. However, existing methods often fail to achieve this balance, yielding representations that are either overly redundant or lacking in task-critical information. We propose an unsupervised approach that learns a highly compressed two-token state representation using a lightweight encoder and a pre-trained Diffusion Transformer (DiT) decoder, capitalizing on its strong generative prior. Our representation is efficient, interpretable, and integrates seamlessly into existing VLA-based models, improving performance by 11.6% on LIBERO and 31% in real-world task success with minimal inference overhead. More importantly, we find that the difference between these tokens, obtained via latent interpolation, naturally serves as a highly effective latent action, which can be further decoded into executable robot actions. This emergent capability reveals that our representation captures structured dynamics without explicit supervision. We name our method StaMo for its ability to learn generalizable robotic Motion from compact State representation, which is encoded from static images, challenging the prevalent dependence to learning latent action on complex architectures and video data. The resulting latent actions also enhance policy co-training, outperforming prior methods by 10.4% with improved interpretability. Moreover, our approach scales effectively across diverse data sources, including real-world robot data, simulation, and human egocentric video.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6889635bdc0ccf254055ad2f5c541b2CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Enhancing Unregistered Hyperspectral Image Super-Resolution via Unmixing-based Abundance Fusion Learning

Zhang, Yingkai, Zhang, Tao, Nie, Jing, Fu, Ying

原文摘要

Unregistered hyperspectral image (HSI) super-resolution (SR) typically aims to enhance a low-resolution HSI using an unregistered high-resolution reference image. In this paper, we propose an unmixing-based fusion framework that decouples spatial-spectral information to simultaneously mitigate the impact of unregistered fusion and enhance the learnability of SR models. Specifically, we first utilize singular value decomposition for initial spectral unmixing, preserving the original endmembers while dedicating the subsequent network to enhancing the initial abundance map. To leverage the spatial texture of the unregistered reference, we introduce a coarse-to-fine deformable aggregation module, which first estimates a pixel-level flow and a similarity map using a coarse pyramid predictor. It further performs fine sub-pixel refinement to achieve deformable aggregation of the reference features. The aggregative features are then refined via a series of spatial-channel abundance cross-attention blocks. Furthermore, a spatial-channel modulated fusion module is presented to merge encoder-decoder features using dynamic gating weights, yielding a high-quality, high-resolution HSI. Experimental results on simulated and real datasets confirm that our proposed method achieves state-of-the-art super-resolution performance. The code will be available at https://github.com/yingkai-zhang/UAFL.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b68c7d0f5cc7654df0ef12b3b422de56CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

BHCast: Unlocking Black Hole Plasma Dynamics from a Single Blurry Image with Long-Term Forecasting

Tu, Renbo, SaraerToosi, Ali, Conroy, Nicholas S., Pekhimenko, Gennady, Levis, Aviad

原文摘要

The Event Horizon Telescope (EHT) delivered the first image of a black hole by capturing the light from its surrounding accretion flow, revealing structure but not dynamics. Simulations of black hole accretion dynamics are essential for interpreting EHT images but costly to generate and impractical for inference. Motivated by this bottleneck, BHCast presents a framework for forecasting black hole plasma dynamics from a single, blurry snapshot, such as those captured by the EHT. At its core, BHCast is a neural model that transforms a static image into forecasted future frames, revealing the underlying dynamics hidden within one snapshot. With a multi-scale pyramid loss, we demonstrate how autoregressive forecasting can simultaneously super-resolve and evolve a blurry frame into a coherent, high-resolution movie that remains stable over long time horizons. From forecasted dynamics, we can then extract interpretable spatio-temporal features, such as pattern speed (rotation rate) and pitch angle. Finally, BHCast uses gradient-boosting trees to recover black hole properties from these plasma features, including the spin and viewing inclination angle. The separation between forecasting and inference provides modular flexibility, interpretability, and robust uncertainty quantification. We demonstrate the effectiveness of BHCast on simulations of two distinct black hole accretion systems, Sagittarius A* and M87*, by testing on simulated frames blurred to EHT resolution and real EHT images of M87*. Ultimately, our methodology establishes a scalable paradigm for solving inverse problems, demonstrating the potential of learned dynamics to unlock insights from resolution-limited scientific data.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6a09e82780815bcafa922ba750cd3b1CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts

Zhu, Zijian, Huang, Qiusheng, Guo, Anboyu, Zhong, Xiaohui, Li, Hao

原文摘要

Current AI weather forecasting models predict conventional atmospheric variables but cannot distinguish between cloud microphysical species critical for aviation safety. We introduce AviaSafe, a hierarchical, physics-informed neural forecaster that produces global, six-hourly predictions of these four hydrometeor species for lead times up to 7 days. Our approach addresses the unique challenges of cloud prediction: extreme sparsity, discontinuous distributions, and complex microphysical interactions between species. We integrate the Icing Condition (IC) index from aviation meteorology as a physics-based constraint that identifies regions where supercooled water fuels explosive ice crystal growth. The model employs a hierarchical architecture that first predicts cloud spatial distribution through masked attention, then quantifies species concentrations within identified regions. Training on ERA5 reanalysis data, our model achieves lower RMSE for cloud species compared to baseline and outperforms operational numerical models on certain key variables at 7-day lead times.The ability to forecast individual cloud species enables new applications in aviation route optimization where distinguishing between ice and liquid water determines engine icing risk.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6c021b76363664679dfc81006e06d6fCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM

Tran, Anh Thuan, Kosecka, Jana

原文摘要

Simultaneous Localization and Mapping (SLAM) with 3D Gaussian Splatting (3DGS) enables fast, differentiable rendering and high-fidelity reconstruction across diverse real-world scenes. However, existing 3DGS-SLAM approaches handle measurement reliability implicitly, making pose estimation and global alignment susceptible to drift in low-texture regions, transparent surfaces, or areas with complex reflectance properties. To this end, we introduce VarSplat, an uncertainty-aware 3DGS-SLAM system that explicitly learns per-splat appearance variance. By using the law of total variance with alpha compositing, we then render differentiable per-pixel uncertainty map via efficient, single-pass rasterization. This map guides tracking, submap registration, and loop detection toward focusing on reliable regions and contributes to more stable optimization. Experimental results on Replica (synthetic) and TUM-RGBD, ScanNet, and ScanNet++ (real-world) show that VarSplat improves robustness and achieves competitive or superior tracking, mapping, and novel view synthesis rendering compared to existing studies for dense RGB-D SLAM.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6caa0c3611db0edd3de5bc2a483c6f3CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis

Zhang, Di, Gong, Zhangpeng, Pang, Xiaobo, Liu, Jiashuai, Lu, Junbo, Cui, Hao, Ge, Jiusong, Zeng, Zhi 等 17 位作者

原文摘要

Foundation models have achieved success in computational pathology, demonstrating generalization across histopathology tasks. However, existing models overlook the heterogeneous and non-uniform organization of regions of interest (ROIs) because they rely on natural image backbones not tailored for tissue morphology. Consequently, they fail to capture the coherent tissue architecture beyond patches, limiting interpretability and clinical relevance. To address these challenges, we present Cross-modal Adaptive Region Encoder (CARE), a foundation model for pathology that partitions WSIs into several morphologically relevant regions. Specifically, CARE employs a two-stage pretraining strategy: (1) a self-supervised unimodal pretraining stage that learns morphological representations from 34,277 whole-slide images (WSIs) without segmentation annotations, and (2) a cross-modal alignment stage that leverages RNA and protein profiles to refine the construction and representation of adaptive regions. This molecular guidance enables CARE to identify biologically relevant patterns and generate irregular yet coherent tissue regions, selecting the representative area as ROI. CARE supports a broad range of pathology-related tasks, using either the ROI feature or the slide-level feature obtained by aggregating adaptive regions. Based on only one-tenth of the pretraining data typically used by mainstream foundation models, CARE achieves superior average performance across 33 downstream benchmarks, including morphological classification, molecular prediction, and survival analysis, and outperforms other foundation model baselines overall.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6e2cf017d03fa364c5a56ebd0501547CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization

Choi, Wonhyeok, Hwang, Kyumin, Park, Jihun, Lee, Kyoungmin, Lee, Seunghun, Kim, Jaeyeul, Choi, Minwoo, Im, Sunghoon

原文摘要

Multi-task learning (MTL) involves the simultaneous optimization of multiple task-specific losses, often leading to gradient conflicts and scale imbalances that result in negative transfer. While existing multi-task optimization methods attempt to mitigate these challenges, they either lack the stochasticity needed to escape poor local minima or fail to explicitly address conflicts at the gradient level. In this work, we propose TaskForce, a novel multi-task optimization framework incorporating cooperative multi-agent reinforcement learning (MARL), where agents learn to find an effective joint optimization strategy based on their respective task gradients and losses. To keep the optimization process compact yet informative, agents observe a summary of the training dynamics that consists of the gradient Gram matrix---capturing both gradient magnitudes and pairwise alignments---and task loss values. Each agent then predicts the balancing parameters that determine the weight of their contribution to the final gradient update. Crucially, we design a hybrid reward function that incorporates both gradient-based signals and loss improvement dynamics, enabling agents to effectively resolve gradient conflicts and avoid poor convergence by considering both direct gradient information and the resulting impact on loss reduction. TaskForce achieves consistent improvements over state-of-the-art MTL baselines on NYU-v2, Cityscapes, and QM9, demonstrating the promise of cooperative MARL in complex multi-task scenarios.

cs.CV · cs.MA

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6e4941b16c2109bcf802489583650ceCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model

Shi, Yukai, Li, Weiyu, Wang, Zihao, Li, Hongyang, Chen, Xingyu, Tan, Ping, Zhang, Lei

原文摘要

We propose a decoupled 3D scene generation framework called SceneMaker in this work. Due to the lack of sufficient open-set de-occlusion and pose estimation priors, existing methods struggle to simultaneously produce high-quality geometry and accurate poses under severe occlusion and open-set settings. To address these issues, we first decouple the de-occlusion model from 3D object generation, and enhance it by leveraging image datasets and collected de-occlusion datasets for much more diverse open-set occlusion patterns. Then, we propose a unified pose estimation model that integrates global and local mechanisms for both self-attention and cross-attention to improve accuracy. Besides, we construct an open-set 3D scene dataset to further extend the generalization of the pose estimation model. Comprehensive experiments demonstrate the superiority of our decoupled framework on both indoor and open-set scenes. Our codes and datasets is released at https://idea-research.github.io/SceneMaker/.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6f4d0a42a2e6ed1aeba263bd75639feCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Coordinate Denoising for Non-Equilibrium Molecular Representation Learning

Tang, Qianwei, Xu, Baile, Zhao, Jian, Shen, Furao

原文摘要

Three-dimensional molecular representation learning has shown great promise in modeling chemical structures and their properties. However, most existing approaches implicitly assume molecules are at or near equilibrium states. This assumption breaks down for non-equilibrium structures--ubiquitous in molecular dynamics (MD) trajectories--where standard coordinate denoising techniques fail because the direct equivalence between denoising scores and atomic forces no longer holds. To bridge this gap, we propose Node Denoising on non-Equilibrium Molecules (NDeM), a novel auxiliary task grounded in a second-order finite difference approximation of the potential energy surface. By explicitly accounting for the non-zero inherent forces in non-equilibrium states, NDeM provides a theoretically sound denoising objective applicable to arbitrary molecular conformations. Crucially, our method is designed as a lightweight, architecture-agnostic plugin that requires no pre-training and can be seamlessly integrated into various supervised learning pipelines. Extensive experiments across diverse benchmarks, including MD17, QM9, and the large-scale OC20 dataset, demonstrate that NDeM consistently improves baseline models, yielding highly competitive performance and validating its robustness across both equilibrium and non-equilibrium regimes.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6f864167180658ef0a104d0ee681f30CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation

Gehlaut, Tarun, Liu, Difan, Bansal, Charu, Malani, Krutik, Chakraborty, Souymodip, Phogat, Ankit, Fisher, Matthew, Batra, Vineet

原文摘要

Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluated on synthetic benchmarks, where clean SVGs are rasterized at high resolution and then re-vectorized. As a result, these methods generalize poorly to real-world scenarios, such as images with unknown rasterization methods or those generated by text-to-image models.We introduce VectorArk, a new VLM-based model designed for robust and practical image vectorization. VectorArk employs a novel rounded polygon representation that simplifies the learning process while naturally producing smooth, visually appealing primitives. We also propose a degradation model that enhances robustness across diverse and imperfect inputs.Our experiments show that, in contrast to previous methods, VectorArk achieves superior geometric completeness and artifact suppression across multiple datasets, with comprehensive ablations validating the contribution of each component.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b6f92ee90805b70bf43b84ddbcaf569bCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

TagSplat: Topology-Aware Gaussian Splatting for Dynamic Mesh Modeling and Tracking

Guo, Hanzhi, Weng, Dongdong, Su, Mo, Chen, Yixiao, Dongye, Xiaonuo, Xu, Chenyu

原文摘要

Topology-consistent dynamic model sequences are essential for applications such as animation and model editing. However, existing 4D reconstruction methods face challenges in generating high-quality topology-consistent meshes. To address this, we propose a topology-aware dynamic reconstruction framework based on Gaussian Splatting. We introduce a Gaussian topological structure that explicitly encodes spatial connectivity. This structure enables topology-aware densification and pruning, preserving the manifold consistency of the Gaussian representation. Temporal regularization terms further ensure topological coherence over time, while differentiable mesh rasterization improves mesh quality. Experimental results demonstrate that our method reconstructs topology-consistent mesh sequences with significantly higher accuracy than existing approaches. Moreover, the resulting meshes enable precise 3D keypoint tracking.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b73b7643b15bf006943076242a49a7b1CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Portable Active Learning for Object Detection

Sharma, Rashi, Bersamin, Justin Timothy C., Subramanian, Karthikk

原文摘要

Annotating bounding boxes is costly and limits the scalability of object detection. This challenge is compounded by the need to preserve high accuracy while minimizing manual effort in real-world applications. Prior active learning methods often depend on model features or modify detector internals and training schedules, increasing integration overhead. Moreover, they rarely jointly exploit the benefits of image-level signals, class-imbalance cues, and instance-level uncertainty for comprehensive selection. We present Portable Active Learning (PAL), a detector-agnostic, easily portable framework that operates solely on inference outputs. PAL combines class-wise instance uncertainty with image-level diversity to guide data selection. At each round, PAL trains lightweight class-specific logistic classifiers to distinguish true from false positives, producing entropy-based uncertainty scores for proposals. Candidate images are then refined using global image entropy, class diversity, and image similarity, yielding batches that are both informative and diverse. PAL requires no changes to model internals or training pipelines, ensuring broad compatibility across detectors. Extensive experiments on COCO, PASCAL VOC, and BDD100K demonstrate that PAL consistently improves label efficiency and detection accuracy compared to existing active learning baselines, making it a practical solution for scalable and cost-effective deployment of object detection in real-world settings.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b7605f4386b5fb1ad0009a34b1f6bdd2CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Material Magic Wand: Material-Aware Grouping of 3D Parts in Untextured Meshes

Jain, Umangi, Kim, Vladimir, Gadelha, Matheus, Gilitschenski, Igor, Chen, Zhiqin

原文摘要

We introduce the problem of material-aware part grouping in untextured meshes.Many real-world shapes, such as scales of pinecones or windows of buildings, contain repeated structures that share the same material but exhibit geometric variations.When assigning materials to such meshes, these repeated parts often require piece-by-piece manual identification and selection, which is tedious and time-consuming.To address this, we propose Material Magic Wand, a tool that allows artists to select part groups based on their estimated material properties -- when one part is selected, our algorithm automatically retrieves all other parts likely to share the same material. The key component of our approach is a part encoder that generates a material-aware embedding for each 3D part, accounting for both local geometry and global context.We train our model with a supervised contrastive loss that brings embeddings of material-consistent parts closer while separating those of different materials;therefore, part grouping can be achieved by retrieving embeddings that are close to the embedding of the selected part.To benchmark this task, we introduce a curated dataset of 100 shapes with 241 part-level queries.We verify the effectiveness of our method through extensive experiments and demonstrate its practical value in an interactive material assignment application.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b76926651c083c4fe9f1da9404721160CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Unsupervised 3d Motion Estimation Using Event Camera

Han, Han, Zhai, Wei, Zhao, Tiesong, Li, Bin, Cao, Yang, Zha, Zheng-jun

原文摘要

Estimating the 3D motion of scene points from 2D observations, typically parameterized by optical flow and motion in depth, is a fundamental problem in computer vision. Existing learning-based methods usually rely on supervised regression from densely labeled data, but their dependence on annotations and limited use of geometric constraints restricts generalization, motivating unsupervised solutions. Unsupervised 3D motion estimation is challenging because motion along the viewing direction is unobservable, and optical flow and motion in depth are geometrically coupled, making their separation ambiguous. Event cameras capture per-pixel brightness changes asynchronously with microsecond latency, providing high temporal resolution and motion continuity. Projecting event streams along different axes reveals spatiotemporal expansion and contraction patterns that encode depth variation and geometric structure, offering rich cues for unsupervised estimation. Leveraging these properties, we propose an unsupervised event-based 3D motion estimation framework that jointly models optical flow and motion in depth. We first derive an analytical relationship to infer initial motion in depth from estimated flow and further refine it using a directional expansion modulation module that captures horizontal and vertical expansion-contraction patterns in event projections. Finally, motion in depth is incorporated into optical flow warping under a contrast maximization objective. Experiments on the CarlaEvent3D dataset show that our method achieves competitive accuracy and strong generalization, advancing unsupervised 3D motion estimation in the event domain.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b77b3a8a3518c646b31ddb293cfaf689CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image

Qiu, Zidian, Wu, Ancong

原文摘要

Current compositional image-to-3D scene generation approaches construct 3D scenes by time-consuming iterative layout optimization or inflexible joint object-layout generation. Moreover, most methods rely on limited field-of-view perspective images, hindering the creation of complete 360^\circ environments. To address these limitations, we design Pano3DComposer, an efficient feed-forward framework for panoramic images. To decouple object generation from layout estimation, we propose a plug-and-play Object-World Transformation Predictor. This module converts the 3D objects generated by off-the-shelf image-to-3D models from local to world coordinates. To achieve this, we adapt the VGGT architecture to Alignment-VGGT by using target object crop, multi-view object renderings and camera parameters to predict the transformation. The predictor is trained using pseudo-geometric supervision to address the shape discrepancy between generated and ground-truth objects. For input images from unseen domains, we further introduce a Coarse-to-Fine (C2F) alignment mechanism for Pano3DComposer that iteratively refines geometric consistency with feedback of scene rendering. Our method achieves superior geometric accuracy for image/text-to-3D tasks on synthetic and real-world datasets. It can generate a high-fidelity 3D scene in approximately 20 seconds on an RTX 4090 GPU. The code will be released if accepted.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b77dce7f60d0233c1e3d9120611e1352CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

ODGS-SLAM: Omnidirectional Gaussian Splatting SLAM

Spiss, Stefan, Hieronimy, Joey, Ritter, Marcel, Harders, Matthias

原文摘要

This work presents ODGS-SLAM, an omnidirectional simultaneous localization and mapping (SLAM) system utilizing 3D Gaussian Splatting (3DGS) as the unified representation for tracking and mapping. Thus, it reconstructs scene geometry from panoramic image sequences (RGB or RGBD) via splats while also estimating the camera poses. Such a framework is important to understand the full surrounding, e.g., for augmented reality applications or autonomous systems. We extended existing 3DGS-SLAM methods to handle omnidirectional input by including closed-form gradients for mapping and camera pose estimation, utilizing an equirectangular projection model. To reduce memory footprint, a key frame removal procedure based on graph analysis is proposed, enabling the application to handle larger input sizes. For evaluation, we provide a dataset of controlled real-world and synthetic test scenes (indoor and outdoor), employing a custom developed virtual camera lens. An extensive evaluation shows that, for camera tracking, the proposed method achieves statistically significant lower ATE RMSE scores compared to a recent omnidirectional SLAM system, as well as other 3DGS-SLAM frameworks, while reaching a similar mapping performance.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b7a620836c2e92b3f712a46a1f8ab332CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models

Qiu, Xingyu, Yang, Mengying, Ma, Xinghua, Liang, Dong, Li, Fanding, Luo, Gongning, Wang, Wei, Wang, Kuanquan 等 9 位作者

原文摘要

Although EDM aims to unify the design space of diffusion models, its reliance on fixed Gaussian noise prevents it from explaining emerging flow-based methods that diffuse arbitrary noise. Moreover, our study reveals that EDM's forcible injection of Gaussian noise has adverse effects on image restoration task, as it corrupts the degraded images, overextends the restoration distance, and increases the task's complexity. To interpret diverse methods for handling distinct noise patterns within a unified theoretical framework and to minimize the restoration distance, we propose EDA, which Elucidates the Design space of Arbitrary-noise diffusion models. Theoretically, EDA expands noise pattern flexibility while preserving EDM's modularity, with rigorous proof that increased noise complexity introduces no additional computational overhead during restoration. EDA is validated on three representative medical image denoising and natural image restoration tasks: MRI bias field correction (global smooth noise), CT metal artifact removal (global sharp noise) and natural image shadow removal (local boundary-aware noise). With only 5 sampling steps, competitive results against specialized methods across medical and natural tasks demonstrate EDA's strong generalization capability for image restoration. Code is available at: https://github.com/PerceptionComputingLab/EDA.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b7e2fdc067ef870dedf478a3883a6a2dCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation

Qian, Jingjing, Han, Boyao, Shi, Chen, Xiao, Lei, Yang, Long, Shi, Shaoshuai, Jiang, Li

原文摘要

Vision-Language-Action (VLA) models achieve strong generalization in robotic manipulation but remain largely reactive and 2D-centric, making them unreliable in tasks that require precise 3D reasoning. We propose GeoPredict, a geometry-aware VLA framework that augments a continuous-action policy with predictive kinematic and geometric priors. GeoPredict introduces a trajectory-level module that encodes motion history and predicts multi-step 3D keypoint trajectories of robot arms, and a predictive 3D Gaussian geometry module that forecasts workspace geometry with track-guided refinement along future keypoint trajectories. These predictive modules serve exclusively as training-time supervision through depth-based rendering, while inference requires only lightweight additional query tokens without invoking any 3D decoding. Experiments on RoboCasa Human-50, LIBERO, and real-world manipulation tasks show that GeoPredict consistently outperforms strong VLA baselines, especially in geometry-intensive and spatially demanding scenarios.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b7e7b13a4837cee1846edbc062932856CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

VRCLIP: Multimodal Canonical Correlation Alignment for CLIP-Driven Vision-Radio Person Re-Identification

Zhang, Rui, Wang, Yaqi, Li, Yadong, Geng, Ruixu, Wang, Jianyang, Ying, Qijun, Zhang, Dongheng, Hu, Yang 等 9 位作者

原文摘要

Multimodal person Re-IDentification (ReID) aims to reliably associate specific individuals by utilizing complementary information from heterogeneous modalities. In contrast, low-frequency radio frequency (RF) signals, with their superior penetration capability and illumination invariance, provide ideal complementary information. However, a key challenge in fusing these heterogeneous modalities lies in the conventional approach that relies heavily on cross-modal distribution matching, which often over-regularizes and weakens the discriminative capacity within each modality. Rather than enforcing direct distribution alignment, canonical correlation analysis (CCA) constructs a shared subspace that maximizes cross-modal correlation, inherently balancing modality specificity and shared semantics. Inspired by this, we reformulate cross-modal alignment as a correlation maximization problem, avoiding direct constraints on feature distributions and guiding the model to harmonize intra-modal discriminative learning with cross-modal alignment. Specifically, VRCLIP first refines CLIP's visual encoder with illumination-disentangling objectives, then aligns RGB and RF embeddings in a canonical correlation subspace, and finally employs an RF-anchored reliability gate for adaptive fusion. To advance the area, we will release VRR, the first large-scale vision-radio ReID dataset with over 650K paired image-radar samples and position annotations for 31 participants. Extensive experiments show state-of-the-art 93.9% mAP and robust generalization across diverse lighting and occlusion conditions.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b7eb65eba365d615febbecd3d9586bbeCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Towards Training-free Scene Text Editing

Li, Yubo, Qin, Xugong, Zhang, Peng, Lin, Hailun, Zeng, Gangyan, Zhang, Kexin

原文摘要

Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require task-specific training or paired data, limiting their scalability and adaptability. In this paper, we propose TextFlow, a training-free scene text editing framework that integrates the strengths of Attention Boost (AttnBoost) and Flow Manifold Steering (FMS) to enable flexible, high-fidelity text manipulation without additional training. Specifically, FMS preserves the structural and style consistency by modeling the visual flow of characters and background regions, while AttnBoost enhances the rendering of textual content through attention-based guidance. By jointly leveraging these complementary modules, our approach performs end-to-end text editing through semantic alignment and spatial refinement in a plug-and-play manner. Extensive experiments demonstrate that our framework achieves visual quality and text accuracy comparable to or superior to those of training-based counterparts, generalizing well across diverse scenes and languages. This study advances scene text editing toward a more efficient, generalizable, and training-free paradigm.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b7efe9e2145c590c4cf5465dcf4e9fb1CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

PDD: Manifold-Prior Diverse Distillation for Medical Anomaly Detection

Lu, Xijun, Liu, Hongying, Shang, Fanhua, Hui, Yanming, Wan, Liang

原文摘要

Medical image anomaly detection faces unique challenges due to subtle, heterogeneous anomalies embedded in complex anatomical structures. Through systematic Grad-CAM analysis, we reveal that discriminative activation maps fail on medical data, unlike their success on industrial datasets, motivating the need for manifold-level modeling. We propose PDD (Manifold-Prior Diverse Distillation), a novel framework that unifies dual-teacher priors into a shared high-dimensional manifold and distills this knowledge into dual students with complementary behaviors. Specifically, frozen VMamba-Tiny and wide-ResNet50 encoders provide global contextual and local structural priors, respectively. Their features are unified through a Manifold Matching and Unification (MMU) module, while an Inter-Level Feature Adaption (InA) module enriches intermediate representations. The unified manifold is distilled into two students: one performs layer-wise distillation via InA for local consistency, while the other receives skip-projected representations through a Manifold Prior Affine (MPA) module to capture cross-layer dependencies. A diversity loss prevents representation collapse while maintaining detection sensitivity. Extensive experiments on multiple medical datasets demonstrate that PDD significantly outperforms existing state-of-the-art methods, achieving improvements of up to 11.8%, 2.9%, and 8.5% in terms of AUROC on HeadCT, BrainMRI, and ZhangLab datasets, respectively, and 3.4% in terms of F1 max on the Uni-Medical dataset, establishing new state-of-the-art performance in medical image anomaly detection. The implementation will be released at https://github.com/OxygenLu/PDD.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b7f18793037db6245af5d9490dff76bdCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD Maps

Zhong, Xuchang, Cao, Xu, Feng, Jinke, Fang, Hao

原文摘要

Visual localization on standard-definition (SD) maps has emerged as a promising low-cost and scalable solution for autonomous driving. However, existing regression-based approaches often overlook inherent geometric priors, resulting in suboptimal training efficiency and limited localization accuracy. In this paper, we propose a novel homography-guided pose estimator network for fine-grained visual localization between multi-view images and standard-definition (SD) maps. We construct input pairs that satisfy a homography constraint by projecting ground-view features into the BEV domain and enforcing semantic alignment with map features. Then we leverage homography relationships to guide feature fusion and restrict the pose outputs to a valid feasible region, which significantly improves training efficiency and localization accuracy compared to prior methods relying on attention-based fusion and direct 3-DoF pose regression. To the best of our knowledge, this is the first work to unify BEV semantic reasoning with homography learning for image-to-map localization. Furthermore, by explicitly modeling homography transformations, the proposed framework naturally supports cross-resolution inputs, enhancing model flexibility. Extensive experiments on the nuScenes dataset demonstrate that our approach significantly outperforms existing state-of-the-art visual localization methods. Code and pretrained models will be publicly available at https://github.com/Quartararo0714/HOLO.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b7f2741afc9e0565766141ae62a9b568CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Re-evaluating Continual VQA: Toward Fair and Robust Evaluation for Multimodal Continual Learning

Gao, Zijian, Sun, Zicheng, Zhang, Xingxing, Xu, Kele, Wang, Huaimin

原文摘要

Continual Visual Question Answering (Continual VQA) poses unique challenges for multimodal continual learning, requiring models to incrementally acquire new knowledge while preserving visual-semantic grounding across tasks. However, existing benchmarks hinder fair and robust evaluation of such capabilities, as they allow models to exploit dataset biases rather than demonstrate genuine continual reasoning. We identify two structural flaws in current benchmark design. First, shared answer vocabularies across tasks encourage answer memorization, inflating performance and underestimating forgetting. Second, static answer priors within each task make the training and test answer distributions nearly identical, obscuring robustness under distribution shifts. To address these issues, we introduce UCo-VQA, an Unbiased benchmark suite that enforces token-level disjoint answer spaces across tasks and introduces intra-task train-test distribution shifts, enabling fairer assessment of forgetting and generalization in multimodal continual learning. We further provide a parameter-efficient baseline that mitigates forgetting and enhances grounding through question-only replay and dual-level distillation, offering a lightweight and memory-efficient framework for continual adaptation. Extensive experiments on UCo-VQA reveal that prior methods substantially overestimate performance under biased setups, while our approach achieves state-of-the-art results, improving robustness and retention by up to 4.18% and 2.21%, respectively.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b804fb4842e00540835cc046dc0e4f21CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

GeoRK2: Geometry-Guided Runge-Kutta Integration for Diffusion Transformer Acceleration

Sun, Chaoqun, Fu, Zongjing, Chang, Powei, Zhang, Jinpeng, Xiang, Jianxiang, Gao, Yukang, Wang, Chenyu

原文摘要

Diffusion transformer models deliver state-of-the-art image synthesis quality but suffer from prohibitively slow iterative sampling. Although reducing sampling steps accelerates inference, aggressive step schedules often distort intermediate features and degrade sample fidelity. We present GeoRK2, a training-free framework that bridges numerical analysis and information geometry. GeoRK2 couples a second-order Runge-Kutta (RK2) integrator with a curvature-aware geometric flow derived from the model's noise predictions, promoting stable feature evolution under manifold-aware integration. By leveraging an empirical feature covariance-induced metric estimated from activation covariances to capture intrinsic feature geometry, GeoRK2 constrains error propagation under large-step integration while preserving structural fidelity. As a fully plug-and-play method, GeoRK2 requires no retraining and is compatible with mainstream pre-trained diffusion transformers. Comprehensive experiments on image generation and text-to-video generation tasks across representative diffusion backbones (e.g., DiT-XL, HunyuanVideo, and FLUX.1-dev) demonstrate that GeoRK2 achieves 4-5x faster inference than baseline frameworks with only marginal perceptual differences (DFID 0.81), confirming its effectiveness and generality.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b813142a390e4d61c013e98fd2123bc2CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Eulerian Gaussian Splatting using Hashed Probability Pyramids

Polansky, Mia Gaia, Kopanas, George, Garbin, Stephan, Zickler, Todd, Verbin, Dor

原文摘要

We introduce a probabilistic splat-based radiance field framework that retains the fast rasterization and test-time efficiency of 3D Gaussian Splatting (3DGS) while replacing heuristic primitive manipulation with gradient-based optimization of a volumetric probability density. Rather than relocating, splitting, or culling Gaussians via hand-tuned densification (e.g., ADC), we treat primitive locations as samples drawn from a persistent, learnable density. We instantiate this density with a novel, memory-efficient multi-scale hierarchical grid that enables end-to-end gradient-based control over primitive population density. To stabilize stochastic training, we derive an unbiased gradient estimator with control variates that markedly reduces variance. By allowing probability mass to flow to where the loss demands, our method eliminates brittle priors and naturally explores the volume, achieving state-of-the-art reconstruction quality on mip-NeRF 360 while preserving 3DGS-level rendering speed.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b825f0be83bb70b8ae71abe03dd298a8CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Customized Fusion: A Closed-Loop Dynamic Network for Adaptive Multi-Task-Aware Infrared-Visible Image Fusion

Yang, Zengyi, Liu, Yu, Cheng, Juan, Zhu, Zhiqin, Zhang, Yafei, Li, Huafeng

原文摘要

Infrared-visible image fusion aims to integrate complementary information for robust visual understanding, but existing fusion methods struggle with simultaneously adapting to multiple downstream tasks. To address this issue, we propose a Closed-Loop Dynamic Network (CLDyN) that can adaptively respond to the semantic requirements of diverse downstream tasks for task-customized image fusion. Specifically, CLDyN introduces a closed-loop optimization mechanism that establishes a semantic transmission chain to achieve explicit feedback from downstream tasks to the fusion network through a Requirement-driven Semantic Compensation (RSC) module. The RSC module leverages a Basis Vector Bank (BVB) and an Architecture-Adaptive Semantic Injection (A2SI) block to customize the network architecture according to task requirements, thereby enabling task-specific semantic compensation and allowing the fusion network to actively adapt to diverse tasks without retraining. To promote semantic compensation, a reward-penalty strategy is introduced to reward or penalize the RSC module based on task performance variations. Experiments on the M3FD, FMB, and VT5000 datasets demonstrate that CLDyN not only maintains high fusion quality but also exhibits strong multi-task adaptability. The code is available at https://github.com/YR0211/CLDyN.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b87c2f4d605e65ff0726029683c00d43CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Exposing and Evaluating Hallucinations for GUI Grounding

Zhang, Zicheng, Jing, Hongyi, Lv, Rui, Fang, Shuo, Zhu, Shiai, Wang, Junying, Li, Chunyi, Liu, Xiaohong 等 10 位作者

原文摘要

Existing GUI benchmarks primarily focus on evaluating models' comprehensive capabilities but largely overlook hallucination phenomena in grounding tasks, which are crucial to the reliability of GUI understanding. In this work, we expose two major types of hallucinations in GUI grounding: 1) Confusion Hallucination, where distractor elements are mistakenly selected, and 2) Fabricated Hallucination, where nonexistent elements are hallucinated with plausible coordinates. To systematically investigate their origins, we introduce GUI-HalluBench, a benchmark comprising two complementary subsets: a parsing subset for assessing structural representation of GUI elements and a hallucination subset for measuring grounding robustness under challenging conditions. This design allows us to associate hallucination patterns with deficiencies in prerequisite abilities: parsing errors are closely tied to both fabricated and confusion hallucinations. Experiments on state-of-the-art models confirm these connections, offering new insights into the root causes of hallucinations and guiding the development of more reliable GUI understanding tools.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:b8879175c0945dcf2ea75eb15903b194CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Toward Early Quality Assessment of Text-to-Image Diffusion Models

Guo, Huanlei, Wei, Hongxin, Jing, Bingyi

原文摘要

Recent text-to-image (T2I) diffusion and flow-matching models can produce highly realistic images from natural language prompts. In practical scenarios, T2I systems are often run in a "generate--then--select" mode: many seeds are sampled and only a few images are kept for use. However, this pipeline is highly resource-intensive since each candidate requires tens to hundreds of denoising steps, and evaluation metrics such as CLIPScore and ImageReward are post-hoc. In this work, we address this inefficiency by introducing Probe-Select, a plug-in module that enables efficient evaluation of image quality within the generation process. We observe that certain intermediate denoiser activations, even at early timesteps, encode a stable coarse structure, object layout and spatial arrangement--that strongly correlates with final image fidelity. Probe-Select exploits this property by predicting final quality scores directly from early activations, allowing unpromising seeds to be terminated early. Across diffusion and flow-matching backbones, our experiments show that early evaluation at only 20% of the trajectory accurately ranks candidate seeds and enables selective continuation. This strategy reduces sampling cost by over 60% while improving the quality of the retained images, demonstrating that early structural signals can effectively guide selective generation without altering the underlying generative model. Code is available at https://github.com/Guhuary/ProbeSelect.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗