Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

• URL: http://arxiv.org/abs/2503.19953v1
• Date: Tue, 25 Mar 2025 17:58:52 GMT
• Title: Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
• Authors: Stefan Stojanov, David Wendt, Seungwoo Kim, Rahul Venkatesh, Kevin Feigelis, Jiajun Wu, Daniel LK Yamins,
• Abstract summary: Estimating motion in videos is an essential computer vision problem with many downstream applications.<n>We develop Opt-CWM, a self-supervised technique for flow and occlusion estimation from a pre-trained next-frame prediction model.<n>We achieve state-of-the-art performance for motion estimation on real-world videos while requiring no labeled data.
• Score: 13.202236467650033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Estimating motion in videos is an essential computer vision problem with many downstream applications, including controllable video generation and robotics. Current solutions are primarily trained using synthetic data or require tuning of situation-specific heuristics, which inherently limits these models' capabilities in real-world contexts. Despite recent developments in large-scale self-supervised learning from videos, leveraging such representations for motion estimation remains relatively underexplored. In this work, we develop Opt-CWM, a self-supervised technique for flow and occlusion estimation from a pre-trained next-frame prediction model. Opt-CWM works by learning to optimize counterfactual probes that extract motion information from a base video model, avoiding the need for fixed heuristics while training on unrestricted video inputs. We achieve state-of-the-art performance for motion estimation on real-world videos while requiring no labeled data.

Related papers

• Future Optical Flow Prediction Improves Robot Control & Video Generation [100.87884718953099]
  We introduce FOFPred, a novel optical flow forecasting model featuring a unified Vision-Language Model (VLM) and Diffusion architecture.<n>Our model is trained on web-scale human activity data-a highly scalable but unstructured source.<n> Evaluations across robotic manipulation and video generation under language-driven settings establish the cross-domain versatility of FOFPred.
  arXiv  Detail & Related papers  (2026-01-15T18:49:48Z)
• mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs [5.109732854501585]
  We introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations.<n>Our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.
  arXiv  Detail & Related papers  (2025-12-17T18:47:31Z)
• FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos [109.99404241220039]
  We introduce FoundationMotion, a fully automated data curation pipeline that constructs large-scale motion datasets.<n>Our approach first detects and tracks objects in videos to extract their trajectories, then leverages these trajectories and video frames with Large Language Models.<n>We fine-tune open-source models including NVILA-Video-15B and Qwen2.5-7B, achieving substantial improvements in motion understanding without compromising performance.
  arXiv  Detail & Related papers  (2025-12-11T18:53:15Z)
• Watch and Learn: Learning to Use Computers from Online Videos [50.10702690339142]
  Watch & Learn (W&L) is a framework that converts human demonstration videos readily available on the Internet into executable UI trajectories at scale.<n>We develop an inverse dynamics labeling pipeline with task-aware video retrieval, generate over 53k high-quality trajectories from raw web videos.<n>These results highlight web-scale human demonstration videos as a practical and scalable foundation for advancing CUAs towards real-world deployment.
  arXiv  Detail & Related papers  (2025-10-06T10:29:00Z)
• AMPLIFY: Actionless Motion Priors for Robot Learning from Videos [29.799207502031496]
  We introduce AMPLIFY, a novel framework that leverages large-scale video data.<n>We train a forward dynamics model on abundant action-free videos and an inverse dynamics model on a limited set of action-labeled examples.<n>In downstream policy learning, our dynamics predictions enable a 1.2-2.2x improvement in low-data regimes, a 1.4x average improvement by learning from action-free human videos, and the first generalization to LIBERO tasks from zero in-distribution action data.
  arXiv  Detail & Related papers  (2025-06-17T05:31:42Z)
• CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning [47.195002937893115]
  CoMo aims to learn more informative continuous motion representations from diverse, internet-scale videos.<n>We introduce two new metrics for more robustly and affordably evaluating motion and guiding motion learning methods.<n>CoMo exhibits strong zero-shot generalization, enabling it to generate continuous pseudo actions for previously unseen video domains.
  arXiv  Detail & Related papers  (2025-05-22T17:58:27Z)
• Pre-Trained Video Generative Models as World Simulators [59.546627730477454]
  We propose Dynamic World Simulation (DWS) to transform pre-trained video generative models into controllable world simulators.<n>To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module.<n> Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models.
  arXiv  Detail & Related papers  (2025-02-10T14:49:09Z)
• E-Motion: Future Motion Simulation via Event Sequence Diffusion [86.80533612211502]
  Event-based sensors may potentially offer a unique opportunity to predict future motion with a level of detail and precision previously unachievable. We propose to integrate the strong learning capacity of the video diffusion model with the rich motion information of an event camera as a motion simulation framework. Our findings suggest a promising direction for future research in enhancing the interpretative power and predictive accuracy of computer vision systems.
  arXiv  Detail & Related papers  (2024-10-11T09:19:23Z)
• Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos [6.093379844890164]
  We propose a novel method to selectively incorporate the physics models with the kinematics observations in an online setting. A recurrent neural network is introduced to realize a Kalman filter that attentively balances the kinematics input and simulated motion. The proposed approach excels in the physics-based human pose estimation task and demonstrates the physical plausibility of the predictive dynamics.
  arXiv  Detail & Related papers  (2024-10-10T10:24:59Z)
• Video Diffusion Models are Training-free Motion Interpreter and Controller [20.361790608772157]
  This paper introduces a novel perspective to understand, localize, and manipulate motion-aware features in video diffusion models. We present a new MOtion FeaTure (MOFT) by eliminating content correlation information and filtering motion channels.
  arXiv  Detail & Related papers  (2024-05-23T17:59:40Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)
• Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning [54.67880602409801]
  In this paper, we study the problem of pre-training world models with abundant in-the-wild videos for efficient learning of visual control tasks. We introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling. Our experiments show that in-the-wild video pre-training equipped with ContextWM can significantly improve the sample efficiency of model-based reinforcement learning.
  arXiv  Detail & Related papers  (2023-05-29T14:29:12Z)
• Reinforcement Learning with Action-Free Pre-Training from Videos [95.25074614579646]
  We introduce a framework that learns representations useful for understanding the dynamics via generative pre-training on videos. Our framework significantly improves both final performances and sample-efficiency of vision-based reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-25T19:44:09Z)
• MotionSqueeze: Neural Motion Feature Learning for Video Understanding [46.82376603090792]
  Motion plays a crucial role in understanding videos and most state-of-the-art neural models for video classification incorporate motion information. In this work, we replace external and heavy computation of optical flows with internal and light-weight learning of motion features. We demonstrate that the proposed method provides a significant gain on four standard benchmarks for action recognition with only a small amount of additional cost.
  arXiv  Detail & Related papers  (2020-07-20T08:30:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.