This work provides a geometric interpretation of FM uncertainty in the velocity field, showing that uncertainty manifests as deviation from an ideal affine-isotropic contraction field, and introduces denoising acceleration ( accel), a highly-generalizable and cost-free uncertainty proxy that measures the bending of the denoising trajectory from a single forward pass.
A Masked Geometric Encoder (MGE) is introduced, which promotes the learning of robust geometric representations under incomplete cross-view context and can achieve inference speedup while consistently maintaining higher reconstruction quality, particularly in limited-view settings.
Zhi-Min Shao, Xi-Jun Liu, Zhao-Liang Zhang et al.· 0 citations
Visual SLAM is commonly evaluated on clean trajectories, although deployment failures are often caused by adverse weather, illumination, blur, and sensor artifacts. Controlled corruptions are attractive because they isolate such factors, but a synthetic stress test is useful only when it leads to the same engineering c...
A. S. Thomas, Shashank Agnihotri, Margret Keuper· 0 citations
Modern video generators routinely fail at physical dynamics: objects float, trajectories violate gravity, contacts vanish. Standard denoising and flow-matching objectives fit visual data distributions but do not explicitly penalize such physical violations. Existing remedies can improve physical consistency, but typica...
Hai Nguyen-Truong, Tuan-Anh Vu, Dang T. Huynh· 2 citations
Flow-Based Distribution Matching is introduced, a non-adversarial framework that learns this reference-directed geometry through spherical conditional velocity regression that achieves performance nearly on par with DM and remains competitive with existing SSL methods.
Yu-Ling Jiao, Wen-Sen Ma, Hou-Duo Qi et al.· 0 citations
Current object pose estimation research remains predominantly model-centric, focusing on architectural innovations and post-processing refinements. This paper introduces a data-centric optimization by proposing a novel, physically grounded rotation representation through principal axes alignment. Our method aligns the...
Wei Chen, Tao Zhen, Zhong-Chen Shi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
