Accurate oriented detection requires boxes to follow object boundaries, yet small errors in the coupled center, size, and angle estimates can displace long boundaries even when an object is correctly classified. We propose NIF, a plug-in refinement branch that represents box geometry with normal-intersection fields. Given a coarse oriented box, it samples local features at 20 boundary anchors and predicts signed distances along their outward normals. These observations have an exact affine representation in five rectangle parameters; a differentiable projection uses error-aware reliability weights to recover a geometrically consistent box. Tangential pooling preserves the normal-position profile, while the shared projection adds 0.132M parameters. On DOTA-v1.0, NIF obtains 77.98%, 79.03%, and 79.32% mAP with Oriented R-CNN, Strip R-CNN, and LSKNet-S, respectively; LSKNet-S gives the strongest single-scale result among the compared methods. NIF also reaches 68.19% mAP on DIOR-R and improves matched FAIR1M-v1.0 and DIOR-R baselines by 0.30% and 0.71%, respectively. On HRSC2016, it raises mean IoU from 0.867 to 0.888 while reducing field error by 24.5%. Finally, with four different detector frameworks frozen, NIF improves relative AP75 by 1.55-4.16% and COCO-style mAP by 0.37-3.76%, without detector retraining. Upon acceptance of this paper, we will publicly release the code at https://github.com/zsk466991125-collab/Normal-Intersection-Fields.
Latent diffusion and flow matching models are ubiquitous in state-of-the-art generative video models. While highly effective, relying on pretrained autoencoders to compress the data into a lower-dimensional latent space also comes with drawbacks. First, training proceeds in two stages: autoencoder pretraining, with compression and reconstruction objectives, followed by latent generative model training, precluding fully end-to-end training. Second, autoencoders also lead to an inherent loss of signal, and the trade-off between reconstruction quality and generative performance in the latent space is still an active area of research. In this paper we explore the viability of generative video models directly in pixel space. We analyze recent approaches in pixel-space generative modeling of images that rely on basic transformer designs, and identify several shortcomings that limit their effectiveness for the high-dimensional pixel-space video generation. To overcome these limitations, we propose a UNet-like transformer architecture along with improvements to the training recipe and sampling strategy. We conduct controlled experiments, training latent and pixel-space models from scratch on Kinetics-600. For the standard frames-to-video task at 128 resolution, our U-JiT model improves generative FVD by 27% over prior state-of-the-art results, and by 14% against the JiT pixel-space baseline. Scaling to higher 256 resolution, we find the improvement over pixel-space and latent-based models grows as we increase the spatiotemporal compression rate up to $64 \times 64 \times 8$. Finally, we find that U-JiT improves per-frame FID by 27% over latent models and 61% over pixel-space models on class-to-video generation, with respectively 9% and 56% reduction in FVD.
Qingguo Hu, Xinyu Ma, Yujie Lin, Yaoxiang Wang, Qi Shi, Zonghao Guo, Chi Chen, Jinsong Su
Fine-grained cross-view localization aims to precisely localize a ground camera against geo-referenced aerial imagery, but current methods typically assume a narrow geographic prior, substantially limiting their applicability when upstream localization remains coarse. To bridge this gap, we study this task over much larger aerial regions. However, this seemingly simple extension fundamentally changes the localization problem: the growing disparity in spatial extent between ground and aerial views makes reliable cross-view matching difficult to establish directly, while the increasing number of look-alike locations in larger regions introduces substantial visual ambiguity. To address these challenges, we propose RingMatch, a search-and-verification framework for wide-area cross-view localization. RingMatch first leverages predictive uncertainty to uncover plausible locations and progressively zooms into their surroundings to obtain increasingly fine-grained evidence, yielding a compact set of promising candidates. We then introduce the depth ring, a novel geometric representation that reveals subtle variations in the spatial layout around a location and serves as a view-shared spatial signature for an LVLM verifier to resolve residual ambiguity. To benchmark this setting, we construct VIGOR-Pro by composing VIGOR aerial tiles into contiguous regions with spatial extents of up to 400 m. Experiments show that RingMatch maintains strong localization performance as the aerial region expands, consistently outperforming representative end-to-end and retrieval-based methods.
Sierra Bonilla, Fengyi Jiang, Chinedu Nwoye, Jingpei Lu, Kailey Reardon, Humphrey W. Chow, Francisco Vasconcelos, Sophia Bano 等 10 位作者
We introduce iMED, the first synchronized multi-endoscope dataset for robot-assisted minimally invasive surgery (RAMIS), designed to address a fundamental limitation in surgical vision benchmarking: the absence of independent held-out viewpoints. Existing surgical datasets capture single-trajectory sequences from a single endoscope, making it impossible to distinguish geometric generalization from photometric interpolation along a narrow forward-facing path. iMED provides 340 sequences ~170K synchronized timepoints with 4 views per timepoint) recorded simultaneously from two independent stereo endoscopes across ex vivo, postmortem, and live surgical settings, spanning 14 specimens with diverse anatomical regions and motion regimes. The dataset includes calibrated camera intrinsics, ArUco-based frame-wise pose estimates with uncertainty quantification, instrument segmentation masks, and rich clinical metadata. Using a train-on-one-endoscope, test-on-another evaluation protocol, we benchmark 23 state-of-the-art methods across rigid and deformable novel view synthesis, pose estimation, feature matching, and monocular depth estimation. Our experiments show that methods relying primarily on photometric supervision degrade substantially under this held-out-endoscope setting, while methods with explicit geometric regularization are more robust across views in our benchmark. Notably, large-scale foundation models transfer surprisingly well to surgical imagery, often outperforming domain-specific models, suggesting pitfalls in current fine-tuning protocols. iMED establishes a new evaluation protocol for geometric generalization in surgical vision.
Recent literature widely used global metrics such as AUROC and AUPRO to quantify the detection performance. AUROC and AUPRO scores are approaching 100% in some public datasets such as MVTec AD dataset and VisA dataset, which misleadingly suggests that the pixel-level anomaly detection task has already been solved. Threshold-independent metrics represented by AUROC inherently ignore the threshold selection process, which is inevitable in practical applications. Although AUPRO restricts the False Positive rates (FPRs) to an acceptable range, extremely low FPRs can lead to increased false negative rates (FNRs). We argue that there is a lack of metrics capable of quantifying the separation between the anomaly score distributions of normal and anomalous samples, which hinders advancements in anomaly detection. In response, we propose the Bounded Area Under the Kolmogorov--Smirnov curve (Bounded AUKS), a partial integral metric that integrates the difference between TPR and FPR within a data-driven bounded range. Specifically, we introduce AUKS from KS integral as a direct measure of separability between the anomaly score distributions. The bounded range is determined only by score distributions of normal test samples. Lower bound excludes the uninformative high-FPR region. Upper bound avoids evaluation in extreme regions that aggressively push FPR towards zero, which result in a very low recall. Our experiments on 9 models across MVTec AD and VisA datasets show that Bounded AUKS can address the limitations of existing metrics and has a better performance in evaluating unsupervised anomaly detection models.
Joshua Offergeld, John Chidiac, Marcel van Gerven, Nasir Ahmad
Node pruning is the art of removing computational units such as neurons, filters, attention heads, or even entire layers to significantly reduce inference time while retaining network performance. In this work, we show that a broad family of importance measures, from activation-based to Fisher-based, share a common quadratic form. Through a lower-triangular change of basis, this form yields a pruning subspace in which entire nodes can be removed while the impact of the lost units is simultaneously recovered via linear least squares. Furthermore, the importance measures within our subspace are decoupled and additive through an orthogonalization of the layer activations, allowing multi-node pruning within layers without interference between importance scores. Our method, Subspace Node Pruning (SNP), outperforms the compared baselines on VGG-16 and ResNet-50 on ImageNet. On OPT-125M and LLaMA-2 7B, SNP matches the state-of-the-art LLM Surgeon at a 40-shot schedule and outperforms it whenever fewer shots are used, all without any retraining after pruning.
Xiang Zhang, Yang Zhang, Lukas Mehl, Karlis Martins Briedis, Markus Gross, Christopher Schroers
Accurately modeling soft boundaries, e.g., hair and defocus blur, is a fundamental challenge in stereo conversion due to the ambiguous blending of foreground and background. Existing depth models primarily predict single-layer depth, leading to ambiguity in depth correspondence at soft boundaries. While matting techniques can capture opacity for layered modeling, they often struggle in complex scenes with multiple targets and usually require user intervention. This paper introduces αDepth, a layered representation that decomposes soft boundaries for high-fidelity stereo conversion. Specifically, we first resolve mixed color and depth ambiguity by estimating layered color and depth values at soft boundaries. Considering complex multi-target scenes, we design a Circular Alpha Representation (CAR) that shifts the paradigm from global target extraction to local boundary decomposition. Unlike prior matting methods restricted to a single foreground/background, CAR enables efficient scene-level inference without manual guidance. Extensive evaluations demonstrate that αDepth achieves state-of-the-art performance in stereo conversion, eliminating background bleeding and structural distortions at soft boundaries.
Muhammad Hamza Zafar, Davit Gigilashvili, Jon Yngve Hardeberg
The reconstruction of fragmented historical textiles presents a significant challenge in computational archaeology. The Oseberg ship burial, dating to 834 CE, yielded hundreds of degraded textile fragments that have resisted systematic computational analysis. While deep learning has revolutionized image-based puzzle solving, progress on archaeological textiles has been limited by the lack of domain-specific datasets and systematic evaluation of modern architectures. To address this gap, we present TEXMET, a curated dataset of 18,644 historical textile images from the Metropolitan Museum of Art's Open Access collection, representing the first textile-specific benchmark for puzzle-solving research. Using TEXMET, we conduct a systematic evaluation of three state-of-the-art puzzle-solving models: JPDVT, FCViT, and DiffAssemble. Our experiments reveal that the transformer-based models pre-trained on standard datasets fail to generalize to textiles, but domain-specific fine-tuning proves highly effective. The graph-based DiffAssemble model, when fine-tuned on TEXMET, achieves 85.89% puzzle accuracy on textile data. Most significantly, applying this fine-tuned model to 45 highly degraded Oseberg fragments yields a performance increase from 26.67% to 64.44% puzzle accuracy. These results establish TEXMET as a new benchmark for textile reconstruction and demonstrate that domain adaptation is essential for applying puzzle-solving methods to imagery of real archaeological materials.
Video Large Language Models (Video-LLMs) have achieved strong performance on many video understanding tasks, yet remain vulnerable to temporal hallucination in time-sensitive reasoning scenarios such as scene transition understanding and event ordering. Existing solutions either require costly retraining or introduce inefficient multi-pass inference and external supervision at test time. In this work, we show that temporal evidence is already encoded in Video-LLM hidden representations but is not fully exploited during standard inference. Motivated by this observation, we propose Single-Pass Orthogonal Decomposition (SPOD), a training-free framework that recovers suppressed temporal evidence through analytical hidden-state manipulation in a single forward pass. SPOD consists of two components: Frame Distinctiveness Analysis (FDA), which identifies salient frames from middle-layer hidden-state geometry, and Temporal Delta Subspace (TDS), which constructs orthogonal temporal and prior subspaces from weighted inter-frame hidden-state differences. By decomposing final hidden states into temporal, prior, and residual components and rescaling them independently, SPOD enhances dynamic information, suppresses static appearance bias, and preserves complementary information. Experiments on VidHalluc, EventHallusion, and VideoMMMU show that SPOD consistently outperforms strong inference-time baselines across temporal reasoning tasks and model architectures while retaining near-vanilla inference efficiency. These results suggest that improving temporal reasoning in Video-LLMs may depend not only on additional supervision, but also on recovering temporal evidence already present in their internal representations. Our code is available at https://github.com/VioAgnes/SPOD.
Recent self-evolution frameworks for video understanding have demonstrated the potential for autonomous improvement from unlabeled videos. However, existing approaches often suffer from weakly controlled optimization and capability progression because they lack structured guidance for generating, evaluating, and reusing supervision throughout the iterative learning process. We present CurEvo, a curriculum-guided self-evolution framework that organizes this loop as a competence-aware progression. Curriculum-Guided Self-Evolution maintains a competence-aware curriculum state and cumulative training pool across iterations. Within this loop, Multi-Dimensional Question Generation supplies complementary supervision, from directly verifiable structural questions for perception to type-conditioned questions for recognition and understanding. Type-Adaptive Evaluation separately assesses question quality and answer reliability with criteria matched to each type's evidence; its scores determine which pairs enter the pool and how the next curriculum state is updated. Across seven backbones and four VideoQA benchmarks, CurEvo consistently improves benchmark accuracy and benchmark semantic score. For Qwen2.5-VL(7B), accuracy rises from 67.84% to 69.91% on ActivityNet-QA and from 76.94% to 79.61% on NExT-QA. CurEvo thus establishes self-generated supervision as a stable route to autonomous video understanding without task-specific human QA annotations during self-evolution.
We propose VT-MUSE, a Multimodal Unified SEquential representation learning framework for visuotactilemanipulation. Existing approaches often encode visual and tactile observations independently before fusion, limiting their ability to capture fine-grained cross-modal dependencies. Moreover, most methods focus on observations at the current time step and overlook the temporal evolution of contact. VT-MUSE addresses both limitations through a two-stage representation learning framework. In Stage I, modality specific encoders are jointly adapted via cross-modal temporal alignment and masked-view consistency. In Stage II, a conditional variational latent model processes masked visual sequences together with full tactile histories. Auxiliary decoders reconstruct the masked recent visual observations and predict tactile depth changes, encouraging the latent representation to retain both global visual context and local contact dynamics. The learned representation is subsequently integrated into a lightweight Transformer policy through gated cross-attention. On the simulation benchmark, VT-MUSE outperforms the strongest baseline evaluated on all tasks by 11 percentage points and also achieves substantial improvements in real-world experiments.
Jeremias Krauß, Pragati Jaiswal, René Schuster, Didier Stricker
Recovering identity-faithful, physically based surface appearance for 3D human heads from sparse images remains challenging. Existing methods often rely on UV-based pipelines, introducing seam artefacts, or operate in image space, limiting surface consistency. We present VISAGE, Vertex-based Intrinsic Surface Appearance GEneration, a surface-based conditional diffusion framework that synthesises per-vertex albedo and roughness directly on arbitrary mesh topologies, without requiring consistent UV parameterisation at training time. VISAGE combines global spectral processing with local geodesic K-Nearest-Neighbour refinement, enforcing structural coherence while restoring detail beyond the truncated spectral basis. Multi-view RGB images condition the network via visibility-aware cross-attention, enabling occlusion-robust synthesis across the full head surface. Region-specific modules specialise in semantically demanding and distinct areas (eyes, mouth, skin and hair), while a tangent-space output projection recovers fine iris detail. We further introduce a scalable procedural augmentation pipeline that enriches raw geometry scans with physically plausible albedo, roughness and normal maps for training. The predicted attributes render directly as a single RGBA vertex-colour channel. VISAGE reduces FID by 42.7% on NPHM and 22.5% and 4.4% on zero-shot FaceVerse and i3DMM, respectively, relative to the strongest baseline, with a 7.2M-parameter core network.
Qinglin Yang, Jiepeng Wang, Yuxing Huang, Haibin Huang, Kai Xu, Chi Zhang, Ruizhen Hu, Xuelong Li
Recent advances in video modeling have driven substantial progress in world action models (WAMs). Existing approaches exploit pretrained video priors by decoding actions from latent representations or inferring them from generated videos. The underlying link is causal: robot actions produce changes in the scene, and video observations of these changes provide evidence for inferring the actions that produced them. However, existing training formulations do not by themselves ensure that actions and their predicted visual consequences are consistent, potentially limiting the use of pretrained capabilities. We treat video and action as paired modalities linked by this causal relationship and learn their correspondence through a unified training framework designed to better exploit pretrained video priors. Cycle WAM first augments video-action co-training with bidirectional conversion to reinforce cross-modal correspondence and recover forward and inverse dynamics. It then introduces a differentiable cycle-reconstruction objective to further couple the two mappings. The resulting model supports both forward and inverse dynamics, with the potential to improve performance through more effective use of pretrained video priors. Cycle WAM achieves state-of-the-art performance among comparable methods on LIBERO-Pro and substantially improves DreamZero on DROID. Comparisons with UWM characterize its inverse-dynamics performance and show sharper visual detail in the displayed forward-dynamics predictions.
Carlo Sgaravatti, Daniele Kopyshevskiy, Davide Secco, Giacomo Boracchi
Multimodal perception is central to many computer vision applications, including robotics and autonomous driving, where different sensing modalities provide complementary cues. Self-supervised learning offers a scalable solution for exploiting large amounts of unlabeled multimodal data. However, existing methods either neglect modality-specific information by enforcing feature-space alignment between modalities or learn only global representations without preserving spatial structure. We propose DenseTwins, a multimodal self-supervised framework that learns dense representations by explicitly decoupling the dense feature space into shared and modality-specific components. The proposed approach combines dense cross-modal correspondences with redundancy-reduction objectives, enabling the model to capture both shared semantics and modality-specific cues within a structured dense embedding space. DenseTwins jointly optimizes an intra-modal objective across augmented views and a cross-modal objective that aligns shared features while decorrelating modality-specific information. We evaluate DenseTwins across multiple multimodal benchmarks and sensing setups, achieving state-of-the-art or competitive performance across multimodal self-supervised baselines. Code available at: https://github.com/CarloSgaravatti/DenseTwins.
Zhong-Shi Zhang, Zi-Li Yu, Xiao Xiao, Huan Liu, Gui-Song Xia, Cui Huang, Meng-Xun Li
Oral photographs contain rich clinical information and hold significant potential for artificial intelligence applications; however, most models are trained for individual tasks and rely on costly expert annotations. We hypothesized that self-supervised training on unlabeled oral photographs could produce transferable visual representations for heterogeneous vision tasks. To test this hypothesis, we developed DOVE (Dental Optical Visual Encoder) by domain-adaptive self-supervised pretraining on approximately 530,000 unlabeled oral photographs collected from publicly accessible sources. DOVE was benchmarked against 3 established baselines across 5 classification datasets and 4 segmentation datasets, covering both frozen backbone evaluation and end-to-end finetuning. DOVE achieved the strongest overall performance, ranking best in few-shot transfer and label efficiency on most benchmarks. Under the 20-shot frozen-backbone protocol, DOVE outperformed the second best DINOv3 by 4.37 percentage points in mean macro-F1 across classification datasets and by 4.49 percentage points in mean macro-Dice across segmentation tasks. Under end-to-end finetuning, DOVE achieved at least 80% of the strongest full-data baseline's performance across most evaluation datasets using only 10% of the labeled training data. Qualitative retrieval and feature analyses further indicated better organization of image-level and spatial representations. These findings support DOVE as a generalizable and label-efficient backbone for oral vision research.
Ligen Shi, Jun Qiu, Zengyu Pang, Yuhang Zheng, Lina Wu, Di He, Chang Liu
Implicit neural representations (INRs) commonly employ Fourier features to alleviate spectral bias and represent high-frequency signals. Fourier encodings, however, use the same frequency representation across spatial locations despite the spatially varying frequency content of natural signals. We propose Adaptive Frequency Implicit Neural Representation (AFINR), a spatially adaptive frequency-conditioning framework for Fourier encoded INRs. A sampling compatible Fourier dictionary first defines the explicit frequency support, and a learnable spatial control field then modulates the admitted Fourier components before decoding. The control field is parameterized in the discrete cosine transform (DCT) domain to provide a compact and continuously queryable spatial representation. AFINR can be combined with different coordinate decoders, including ReLU, SIREN, CAFE, and CAFE+. Experiments on Kodak and DIV2K show consistent average improvements across these decoder families. In particular, AFINR-CAFE+ improves CAFE+ by 3.95 dB on Kodak and 3.50 dB on DIV2K. Ablation studies characterize the effects of adaptive-field parameterization, DCT coefficient retention, and frequency-response parameters, while learned spatial responses show position-dependent use of the admitted Fourier components.
Multi-modal image fusion (MMIF) aims to form a single image by integrating shared information, preserving complementary cues, and coordinating cross-modal conflicts across modalities. However, due to the absence of ground-truth fused images, existing MMIF supervision commonly uses spatial-domain sources or gradient variants as surrogate ground truths, making the supervision mechanism inherently misaligned with the goal of MMIF and causing pixel-level compromise or modality bias. To address this, we propose a relation-constrained supervision paradigm that moves fusion supervision from the spatial domain to a learned relation space. Instead of forcing the fused image to approximate the sources, we use frozen pretrained representation models as information providers and design a learnable feature adapter to align heterogeneous DINO and CLIP features into a unified supervision space. The adapter infers three relation parameters, namely sharedness, dominance, and coordination radius, which define three losses corresponding to the MMIF's goal. To make this space reliable, we devise a self-supervised contrastive ranking objective tailored to the adapter and couple it with the fusion network through alternating optimization. Extensive experiments show that the proposed supervision space yields significant gains regardless of which mainstream backbone the fusion network adopts, offering a supervision paradigm better aligned with the goal of MMIF. Code: github.com/GMY628/RCS-Fusion.
Hierarchical 3D grouping aims to recover scene groups across multiple granularities, from fine object parts to complete objects, without relying on semantic labels or a fixed vocabulary. The main challenge is to transform 2D foundation-model cues into coherent hierarchy supervision and embed that hierarchy in a 3D representation. We propose H2G, a hyperbolic affinity field for hierarchical 3D grouping. Our method derives semantically organized tree supervision by interpreting foundation-model affinities through Dasgupta's objective for similarity-based hierarchical clustering. This supervision is distilled into a single Lorentz hyperbolic feature field, whose geometry is well suited for tree-like branching structures. A hierarchy-aware objective aligns the field with fine-level assignments, coarse object structure, compact feature clusters, and LCA (Lowest Common Ancestor) ordering. This formulation represents multiple grouping levels in one feature space, enabling semantic hierarchical grouping grounded in 2D foundation-model knowledge. Code is available at https://github.com/Rhqo/H2G.
Ku Onoda, Paavo Parmas, Hiroki Furuta, Soichiro Nishimori, Yuta Oshima, Shohei Taniguchi, Yutaka Matsuo
Text-to-image (T2I) models produce realistic, prompt-aligned images, but samples for the same prompt often cover only a few visually distinct modes. For person-centric prompts, this lack of diversity can reflect or amplify demographic skew. We formalize representative diversity as target-mode coverage: how well a set of samples covers predefined modes, such as colors or perceived-race categories. We then propose MultiMaxPO, a reinforcement learning post-training method that improves this coverage in diffusion T2I models by optimizing a multi-axis max@K objective. Given one score per mode for each sample, multi-axis max@K takes the maximum over samples for each mode and then sums these maxima. A sample therefore receives credit for a mode only when it raises that mode's maximum, so different samples are rewarded for different modes. We verify this credit assignment on a synthetic Gaussian mixture and on Stable Diffusion 3.5 Medium with pixel-based color rewards, and then apply it to perceived-appearance fairness. On held-out prompts and under three automatic evaluators, MultiMaxPO improves the Fairness Score over the base model by 0.22-0.36 on Stable Diffusion 3.5 Medium and by 0.07-0.19 on FLUX.1-dev, outperforms matched RL baselines, and maintains image quality and text alignment. Code is available at https://github.com/KuOnoda/multi-axis-maxk.
Baris Oguz, Xing Yao, Claudia Tawil, Alison Pouch, Brett Byram, Gabriel Arenas, Nadav Schwartz, Ipek Oguz
Convolutional neural networks (CNN) are widely used for medical image segmentation. However, they lack an inherent measure of confidence. Existing methods for estimating prediction uncertainty often require a custom network architecture and/or dedicated training setups and need to be trained from scratch. In addition, the deduction of a single confidence score per input from the uncertainty maps is not always straightforward. In this study, we explore voxel-based uncertainty estimation methods that can be added to existing segmentation pipelines without training from scratch. We also propose a novel method to estimate a single confidence score from the uncertainty maps. Our evaluations on different ROIs and modalities suggest that our confidence score can predict segmentation performance in unseen data.
Hosung Jeon, Jun Young Jeong, Sangwoon Kwak, Joonsoo Kim, Sangmin Kim, Jaesik Park, Won-Sik Cheong, Hyon-Gon Choo
Spatiotemporal scene reconstruction with Dynamic Gaussian Splatting (DGS) fundamentally depends on perfect temporal synchronization across all cameras, an assumption rarely achievable in practice. Industry-standard synchronization requires expensive specialized hardware and complex setup, while data-driven alternatives including audio-based alignment, geometry matching, and pose tracking remain limited by restrictive environmental or scene-specific assumptions. To overcome these limitations, we propose Phase-DGS, a framework that replaces conventional timestamps with a semantic phase representing each frame's inherent state within the underlying motion cycle. Frames capturing the same motion state share the same phase regardless of which camera records them or when, naturally establishing spatiotemporal correspondence across unsynchronized cameras. We validate Phase-DGS under temporal offsets, frame drops, and camera freezes, achieving up to +8.5 dB PSNR improvement over baselines while enabling seamless integration with existing DGS backbones including RealTime-4DGS and FreeTimeGS.
We formalize and enable the task of open tree decomposition, which segments an image into hierarchical trees of visual components with unconstrained granularity and flexibility. Specifically, we provide the foundation benchmark for this new paradigm with the following three key contributions. First, we overcome the prohibitively high cognitive and physical bottlenecks of manual annotation by developing a fully automated generation pipeline that synergizes the semantic reasoning of Large Vision-Language Models (LVLMs) with the precise geometric grounding of SAM 3. Second, leveraging this pipeline, we construct COCOTree, a massive-scale benchmark featuring over 21K images and 1.8M structural nodes. By embracing an open-vocabulary space of over 3.5K unique labels, it successfully captures the long-tail distribution of complex physical assemblies. Notably, rigorous human evaluation confirms our generated annotations demonstrate strong alignment with human structural judgment. Third, we establish a standardized evaluation protocol by proposing the Open Tree Quality (OTQ) metric, which jointly assesses mask precision, label accuracy, and structural consistency. We release our dataset and benchmark code at https://github.com/melonkick3090/COCOTree.
We introduce BhopalMLS, a large-scale Mobile Laser Scanning (MLS) dataset from a dense, heterogeneous urban environment in Bhopal, India, with mixed traffic, informal structures, and narrow unplanned streets. It spans approximately 10 km of road corridors with over 1.2 billion points and 19,518 annotated instances across 62 fine-grained static categories, grouped into 12-class and 21-class benchmark taxonomies; 6 optional moving-class subclasses support dynamic-object analysis. Existing 3D datasets, collected in well-planned cities, are structurally more uniform than such unplanned settings, and lack their subtype diversity. On semantic and instance segmentation at both granularities, fine-tuned foundation models surpass supervised baselines: Utonia(L) reaches 71.28% mIoU (vs. PTv3's 68.04% from scratch) and 44.07% mAP50 on the 12-class benchmark. Cross-region experiments against four established datasets (Ke-MLS, Toronto-3D, Paris-Lille-3D, SemanticKITTI) reveal a consistent asymmetric transferability: models trained on BhopalMLS transfer better than the reverse on every pair, for both Utonia(L) and Concerto(L) (mean 21.5, up to 36 mIoU points), holding even when the target is denser. Factor-controlled retraining at a fixed label budget, repeated on both models, attributes this to the coverage of BhopalMLS's subtype inventory rather than to dataset size or corridor geometry: collapsing each class to a single subtype costs 13.0 and 13.3 mIoU points for Utonia(L) and Concerto(L). BhopalMLS therefore offers a testbed for 3D perception beyond well-planned cities. Data and an interactive viewer are at https://geoai4cities.github.io/bhopalmls.
Modern image editors excel at semantic manipulation and visual synthesis, yet remain limited in precise spatial control, motivating the development of drag-based editing. However, existing drag-based methods often struggle to balance drag accuracy with natural, plausible, and intent-aligned generation. We propose MoRe-Drag, a motion-grounded drag-based editing method. Our key insight is to treat pixel-space warping as coarse motion evidence, and to inject this evidence into the generative sampling trajectory. Specifically, MoRe-Drag performs region-aware latent recomposition over refinement, inpainting, and preservation regions, coupled with stage-adaptive conditioning that progressively shifts from motion-grounded structure formation to semantic refinement. We further support a no-manual-instruction interface by adapting the MLLM-based text encoder for drag-aware instruction inference. Experiments on DragBench-SR and DragBench-DR show that MoRe-Drag substantially improves drag precision over strong base editors and achieves superior drag accuracy among SOTA drag-based methods, while delivering strong semantic consistency and visually realistic results. Project page: https://xinyu-pu.github.io/projects/more-drag/.
We report the end-to-end deployment and measurement of MiniMax H3, a 20.38-billion-parameter video diffusion transformer (DiT) - the count measured from the safetensors headers of the Q8 checkpoint as deployed locally (Section 3.2) - running entirely on consumer Apple Silicon hardware: an Apple Mac mini with M5 Pro chip and 64 GiB of unified memory. Using the official bf16-to-Q8 (8-bit, group size 64) quantization path executed locally on the machine, we produced a working text-to-video pipeline with no cloud dependency. We document the full deployment procedure, including two non-trivial blockers and their fixes, and report measured figures for build time, peak memory, and per-clip render latency across four resolution tiers (Draft 384x640 through Native 768x1344). A 15.08-second 576x1024 clip rendered in 4838.49 seconds with a measured MLX peak of 27.467 GiB. We further operated the system as an unattended production pipeline, completing 17 clips in 26.49 hours with zero render failures. A blind human review of the 17 production clips (generation prompts withheld) averaged 3.12, 3.18, and 2.94 out of 5 for structural integrity, temporal consistency, and visible artifacts. All figures in this report are our own measurements except where explicitly labeled as third-party data. This is a systems/empirical report; we make no claim of model innovation.
Dominik Schnaus, Thomas Dagès, Daniel Cremers, Xi Wang, Phillip Isola
Multimodal representations enable zero-shot classification and retrieval, but aligning independently trained models usually requires large amounts of paired data. Yet, the Platonic Representation Hypothesis suggests that models trained on different modalities may converge spontaneously toward a shared representation geometry. But then, do we even need paired examples for cross-modal alignment? Remarkably, we show that paired examples are unnecessary for coarse cross-modal alignment. Our simple Wasserstein Procrustes method with a coarse geometric initialization (GeoWarP) aligns two disjoint embedding sets by estimating a single orthogonal map without seeing any pairs. Across datasets, modalities, and unimodal models, we show that we can consistently align independently trained representations without pairs, and standard geometric alignment metrics accurately predict when this is possible. Nevertheless, we can naturally benefit from paired examples. In the very few-pair regime, our method substantially outperforms existing ones, while staying competitive with pair-based methods with more added examples. Finally, we demonstrate that the resulting alignments can enable text-to-image generation without paired examples. These results show that independently trained models often share enough geometry to establish cross-modal correspondence with little or no paired data.
Qijian Zheng, Wanqing Lin, Yuanfang Wang, Yijun Ge, Jordan Bate, Katie Aafjes-van Doorn, Feng Liu
Facilitative Interpersonal Skills (FIS) is a performance-based assessment method that provides a structured framework for evaluating the interpersonal competencies of mental health professionals. However, existing FIS assessment relies heavily on human observer ratings, making the evaluation process labor-intensive, costly, and difficult to scale. Progress toward automated FIS assessment has also been constrained by the lack of publicly available professional data in psychotherapy settings. To address this limitation, we introduce Therapy-FIS, a dataset for automated FIS assessment in standardized psychotherapy tasks. To our knowledge, Therapy-FIS is the first publicly available dataset in this domain. It contains facial, acoustic, and textual signals derived from standardized therapist responses to standardized mock patient stimulus clips, based on 890 therapist video recordings and 8 patient videos, and is rated with eight FIS subscale ratings and an overall FIS score. Built on Therapy-FIS, we further establish a benchmark with two downstream tasks: Therapist Performance Rating and Joint Therapist--mock-Patient Performance Rating. We also introduce a competitive baseline, DyadicFIS, with gated fusion and routed readout under therapist-only and dyadic settings. DyadicFIS obtains the best macro CCC(Concordance Correlation Coefficient) scores on both tasks (0.2807 and 0.3299). Therapy-FIS offers a reproducible resource for data-driven automated assessment of therapeutic interpersonal skills in mental health.
Learning humanoid skills from videos typically requires a successful human demonstration, which often demands custom data collection. Although failures have traditionally been treated only as negative examples in robot learning, they can still reveal a usable trajectory prefix before the task fails, as well as the intended outcome. To leverage this information from a failed-attempt video, we propose TRACC, a pipeline that imitates the useful portion of the motion trajectory and then completes the task based on the inferred task outcome. The usable motion prefix serves as prior knowledge until the failure occurs, after which the task-completion reward guides the policy to learn the intended task goal without requiring a successful task trajectory. We evaluate our method on six in-the-wild failed human tasks from the Oops! dataset. Our experimental results demonstrate the effectiveness of the proposed approach for learning from failed attempts when no successful demonstration is available. Thus, these findings establish failed human videos as a viable source of supervision for humanoid skill learning.
Deep neural networks deployed on smart glasses must adapt to changes in the distribution of incoming data while adhering to strict privacy and device constraints. We present No Frames, Just Frequencies, a bandwidth-efficient source-assisted adaptation framework that characterizes distribution shifts using compact frequency descriptors computed on-device. Rather than transmitting camera frames, the glasses compute and send frequency descriptors to a host device that contains a replica of the model. The host device maps the received frequency descriptor to a distribution shift operator that synthesizes out-of-distribution data and adapts a model replica using a pre-defined adaptation protocol. We evaluate the framework on mixtures of ImageNet-C corruptions using convolution-based (ConvNeXtV2-Femto), self-attention-based (DeiT-Tiny), and hybrid (TinyViT-5M) vision models, on person classification (Visual Wake Words), and on object detection (MS-COCO). Our results reveal that adaptation driven solely by the transmitted descriptors recovers $93-95\%$ of the supervised oracle adaptation gain on all three architectures, $82\%$ on Visual Wake Words and $94$--$98\%$ on MS-COCO. Notably, adaptation quality degrades gracefully as the descriptor resolution decreases from $224 $ to $28$ pixels, consistently across architectures, enabling bandwidth reductions from $213\times$ to $784\times$ across the frequency descriptors.
Video character replacement aims to replace actors while preserving facial expressions, motions, and scene dynamics. Existing methods typically rely on masked generation with pose guidance, limiting fine-grained expression and motion preservation in complex scenes. We propose ReXMo, an end-to-end framework that supports single-, multi-, and selective character replacement scenarios. ReXMo introduces paired triplet supervision, where synthesized driving videos and original videos share identical performances but different identities, enabling scalable training through synthetic data generation. An In-Context Diffusion Transformer learns identity transformation by jointly conditioning on driving videos, reference identities, and text prompts, while an Expression Enhancement Adapter improves facial expression preservation in multi-person scenes. Extensive experiments demonstrate that ReXMo outperforms existing methods in identity fidelity, motion consistency, expression preservation, and visual quality. Our dataset and code will be publicly released.