{"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/nvfi-neural-velocity-fields-for-3d-physics-1","title":"NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos","arxiv_id":"2312.06398","date":"2023-12-11","proceeding":"NeurIPS 2023 11","authors":["Jinxi Li","Ziyang Song","Bo Yang"],"abstract":"In this paper, we aim to model 3D scene dynamics from multi-view videos. Unlike the majority of existing works which usually focus on the common task of novel view synthesis within the training time period, we propose to simultaneously learn the geometry, appearance, and physical velocity of 3D scenes only from video frames, such that multiple desirable applications can be supported, including future frame extrapolation, unsupervised 3D semantic scene decomposition, and dynamic motion transfer. Our method consists of three major components, 1) the keyframe dynamic radiance field, 2) the interframe velocity field, and 3) a joint keyframe and interframe optimization module which is the core of our framework to effectively train both networks. To validate our method, we further introduce two dynamic 3D datasets: 1) Dynamic Object dataset, and 2) Dynamic Indoor Scene dataset. We conduct extensive experiments on multiple datasets, demonstrating the superior performance of our method over all baselines, particularly in the critical tasks of future frame extrapolation and unsupervised 3D semantic scene decomposition.","url_abs":"https://arxiv.org/abs/2312.06398v1","url_pdf":"https://arxiv.org/pdf/2312.06398v1.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":[{"paper_slug":"nvfi-neural-velocity-fields-for-3d-physics-1","repo_url":"https://github.com/vlar-group/nvfi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.06398","atlas_url":"https://app.syntology.ai/?focus=2312.06398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06398"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/vLAR-group/NVFi","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vlar-group/nvfi","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"8b2cfe9399727b55","entry":"NVFi","repo":"vlar-group/nvfi","repo_kind":"official","path":"models/nvfi.py","file_url":"https://github.com/vlar-group/nvfi/blob/HEAD/models/nvfi.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"8b2cfe9399727b55"}},{"code_sha256_prefix":"774fa891bb692b69","entry":"load_model_checkpoint","repo":"vLAR-group/NVFi","repo_kind":"official","path":"train_nvfi.py","file_url":"https://github.com/vLAR-group/NVFi/blob/HEAD/train_nvfi.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"774fa891bb692b69"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}