{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/shape-of-motion-4d-reconstruction-from-a","title":"Shape of Motion: 4D Reconstruction from a Single Video","arxiv_id":"2407.13764","date":"2024-07-18","proceeding":null,"authors":["Qianqian Wang","Vickie Ye","Hang Gao","Jake Austin","Zhengqi Li","Angjoo Kanazawa"],"abstract":"Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task. Existing approaches are limited in that they either depend on templates, are effective only in quasi-static scenes, or fail to model 3D motion explicitly. In this work, we introduce a method capable of reconstructing generic dynamic scenes, featuring explicit, full-sequence-long 3D motion, from casually captured monocular videos. We tackle the under-constrained nature of the problem with two key insights: First, we exploit the low-dimensional structure of 3D motion by representing scene motion with a compact set of SE3 motion bases. Each point's motion is expressed as a linear combination of these bases, facilitating soft decomposition of the scene into multiple rigidly-moving groups. Second, we utilize a comprehensive set of data-driven priors, including monocular depth maps and long-range 2D tracks, and devise a method to effectively consolidate these noisy supervisory signals, resulting in a globally consistent representation of the dynamic scene. Experiments show that our method achieves state-of-the-art performance for both long-range 3D/2D motion estimation and novel view synthesis on dynamic scenes. Project Page: https://shape-of-motion.github.io/","url_abs":"https://arxiv.org/abs/2407.13764v1","url_pdf":"https://arxiv.org/pdf/2407.13764v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"4d-reconstruction","task_name":"4D reconstruction"},{"task_slug":"dynamic-reconstruction","task_name":"Dynamic Reconstruction"},{"task_slug":"motion-estimation","task_name":"Motion Estimation"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dynamic-reconstruction-on-iphone-dataset","task":"Dynamic Reconstruction","dataset":"iPhone (Monocular Dynamic View Synthesis)","model":"Shape-of-Motion","rank_in_archive_order":2,"of":7,"metrics":{"LPIPS":"0.39"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.13764","atlas_url":"https://app.syntology.ai/?focus=2407.13764","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}