collaborators

6 papers

cs.CV2025

Autoregressive Flow Matching for Motion Prediction

Johnathan Xie, Stefan Stojanov, Cristobal Eyzaguirre +2

Motion prediction has been studied in different contexts with models trained on narrow distributions and applied to downstream tasks in human motion prediction and robotics. Simult…

cs.CV2025

World Modeling with Probabilistic Structure Integration

Klemen Kotar, Wanhee Lee, Rahul Venkatesh +13

We present Probabilistic Structure Integration (PSI), a system for learning richly controllable and flexibly promptable world models from data. PSI consists of a three-step cycle.…

cs.CV2025

Weakly-Supervised Learning of Dense Functional Correspondences

Stefan Stojanov, Linan Zhao, Yunzhi Zhang +2

Establishing dense correspondences across image pairs is essential for tasks such as shape reconstruction and robot manipulation. In the challenging setting of matching across diff…

cs.CV2025

Discovering and using Spelke segments

Rahul Venkatesh, Klemen Kotar, Lilian Naing Chen +10

Segments in computer vision are often defined by semantic considerations and are highly dependent on category-specific conventions. In contrast, developmental psychology suggests t…

cs.CV2025

Taming generative video models for zero-shot optical flow extraction

Seungwoo Kim, Khai Loong Aw, Klemen Kotar +8

Extracting optical flow from videos remains a core computer vision problem. Motivated by the recent success of large general-purpose models, we ask whether frozen self-supervised v…

cs.CV2025

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

Stefan Stojanov, David Wendt, Seungwoo Kim +4

Estimating motion in videos is an essential computer vision problem with many downstream applications, including controllable video generation and robotics. Current solutions are p…