Papers › Unsupervised Learning of Object Structure and Dynamics from Videos
Unsupervised Learning of Object Structure and Dynamics from Videos
Matthias Minderer, Chen Sun, Ruben Villegas, Forrester Cole, Kevin Murphy, Honglak Lee
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stochastic dynamics model of the keypoints. Future frames are reconstructed from the keypoints and a reference frame. By modeling dynamics in the keypoint coordinate space, we achieve stable learning and avoid compounding of errors in pixel space. Our method improves upon unstructured representations both for pixel-level video prediction and for downstream tasks requiring object-level understanding of motion dynamics. We evaluate our model on diverse datasets: a multi-agent sports dataset, the Human3.6M dataset, and datasets based on continuous control tasks from the DeepMind Control Suite. The spatially structured representation outperforms unstructured representations on a range of motion-related tasks such as object tracking, action recognition and reward prediction.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_citation_path(paper_1="1906.07889", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1906.07889")
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Video Prediction | KTH | Struct-VRNN (from Grid-keypoints) | Cond | 10 | #11 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | Struct-VRNN (from Grid-keypoints) | FVD | 395.0 | #11 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | Struct-VRNN (from Grid-keypoints) | LPIPS | 0.124 | #11 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | Struct-VRNN (from Grid-keypoints) | PSNR | 24.29 | #11 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | Struct-VRNN (from Grid-keypoints) | Params (M) | 2.3 | #11 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | Struct-VRNN (from Grid-keypoints) | Pred | 40 | #11 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | Struct-VRNN (from Grid-keypoints) | SSIM | 0.766 | #11 of 31 | Archive leaderboard | report |
| Video Prediction | KTH | Struct-VRNN (from Grid-keypoints) | Train | 10 | #11 of 31 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections