Tempered Self-Similarity Alignment for Physically Plausible Video Generation

May 24, 2026 ยท Grace Period ยท ๐Ÿ› the CVPR 2026 Workshop on Video Generative Models: Benchmarks and Evaluation

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Manjin Kim, Suha Kwak, Minsu Cho arXiv ID 2605.24962 Category cs.CV: Computer Vision Citations 0 Venue the CVPR 2026 Workshop on Video Generative Models: Benchmarks and Evaluation
Abstract
Despite remarkable advances in video generative models, they still struggle to generate physically realistic videos, frequently exhibiting appearance drift, implausible motion, and temporal inconsistencies. In this work, we address this limitation by transferring relational knowledge encoded in spatio-temporal self-similarity (STSS) from visual foundation models into video generative models. STSS represents pairwise similarities among features across space and time, revealing the relational structure of how objects interact with other entities throughout a video, effectively capturing real-world dynamics, including object motion and semantic transformations. To transfer this relational knowledge, we propose Tempered Self-similarity Alignment (TSA) loss, which transforms STSS into probabilistic correspondence distributions and trains the video generative model to align its correspondence distributions with those of the visual foundation model on dynamically changing regions. Evaluated on VideoPhy and VideoPhy2 benchmarks, our method demonstrates substantial improvements in physical plausibility across diverse interaction scenarios, validating the effectiveness of transferring relational knowledge for physically realistic video generation.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision

๐ŸŒ… ๐ŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV ๐Ÿ› ICCV ๐Ÿ“š 27.7K cites 11 years ago