跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.26433 · v1

AdaPixFlow: Learning Continuous-Time 3D Dynamics Across Scenes from Sparse Multi-view Observations

首次提交 2026-11-20 01:09
版本更新 2026-11-20 01:09
雷达观测 2026-11-20 12:52
arXiv ↗PDF ↗

摘要

Understanding how objects move in dynamic scenes requires recovering their 3D motion from visual observations and predicting their positions at unobserved times. Existing methods either optimize scene-specific velocity fields or impose predefined physical and kinematic assumptions. We instead study learning a continuous-time dynamics operator across scenes, mapping multi-view visual observations to 3D object kinematics. We introduce Adaptive Pixel Flows (\ours{}), which learns this operator from multi-view RGB-D observations without per-scene optimization or predefined motion models. The method fuses observations from all cameras into a shared voxel grid in world coordinates, from which the network predicts a continuous-time velocity field. Because the operator is trained across scenes, it learns motion priors that carry over to unseen scenes. The field can then be integrated from observed states to predict object positions between observations and beyond the observed sequence. On held-out PhysInOne scenes, \ours{} improves F1 over the strongest competing method by 2.5\% for in-between prediction and 15\% for future prediction. Compared with per-scene velocity-field methods, the improvements are 30\% and 85\%, respectively. Applied zero-shot to Spring-Gaus, it improves future-prediction F1 by 12\%.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-20 01:09 · 最新观测版本

AdaPixFlow: Learning Continuous-Time 3D Dynamics Across Scenes from Sparse Multi-view Observations

Understanding how objects move in dynamic scenes requires recovering their 3D motion from visual observations and predicting their positions at unobserved times. Existing methods either optimize scene-specific velocity fields or impose predefined physical and kinematic assumptions. We instead study learning a continuous-time dynamics operator across scenes, mapping multi-view visual observations to 3D object kinematics. We introduce Adaptive Pixel Flows (\ours{}), which learns this operator from multi-view RGB-D observations without per-scene optimization or predefined motion models. The method fuses observations from all cameras into a shared voxel grid in world coordinates, from which the network predicts a continuous-time velocity field. Because the operator is trained across scenes, it learns motion priors that carry over to unseen scenes. The field can then be integrated from observed states to predict object positions between observations and beyond the observed sequence. On held-out PhysInOne scenes, \ours{} improves F1 over the strongest competing method by 2.5\% for in-between prediction and 15\% for future prediction. Compared with per-scene velocity-field methods, the improvements are 30\% and 85\%, respectively. Applied zero-shot to Spring-Gaus, it improves future-prediction F1 by 12\%.

查看此版本解读 →查看此版本原文 ↗