{"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/human-motion-diffusion-as-a-generative-prior","title":"Human Motion Diffusion as a Generative Prior","arxiv_id":"2303.01418","date":"2023-03-02","proceeding":null,"authors":["Yonatan Shafir","Guy Tevet","Roy Kapon","Amit H. Bermano"],"abstract":"Recent work has demonstrated the significant potential of denoising diffusion models for generating human motion, including text-to-motion capabilities. However, these methods are restricted by the paucity of annotated motion data, a focus on single-person motions, and a lack of detailed control. In this paper, we introduce three forms of composition based on diffusion priors: sequential, parallel, and model composition. Using sequential composition, we tackle the challenge of long sequence generation. We introduce DoubleTake, an inference-time method with which we generate long animations consisting of sequences of prompted intervals and their transitions, using a prior trained only for short clips. Using parallel composition, we show promising steps toward two-person generation. Beginning with two fixed priors as well as a few two-person training examples, we learn a slim communication block, ComMDM, to coordinate interaction between the two resulting motions. Lastly, using model composition, we first train individual priors to complete motions that realize a prescribed motion for a given joint. We then introduce DiffusionBlending, an interpolation mechanism to effectively blend several such models to enable flexible and efficient fine-grained joint and trajectory-level control and editing. We evaluate the composition methods using an off-the-shelf motion diffusion model, and further compare the results to dedicated models trained for these specific tasks.","url_abs":"https://arxiv.org/abs/2303.01418v3","url_pdf":"https://arxiv.org/pdf/2303.01418v3.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":"human-motion-diffusion-as-a-generative-prior","repo_url":"https://github.com/priormdm/priormdm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"human-motion-diffusion-as-a-generative-prior","repo_url":"https://github.com/zhenzhiwang/intercontrol","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/motion-synthesis-on-inter-x","task":"Motion Synthesis","dataset":"Inter-X","model":"ComMDM","rank_in_archive_order":6,"of":6,"metrics":{"FID":"29.266","MMDist":"6.870","MModality":"0.771","R-Precision Top3":"0.236"},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-interhuman","task":"Motion Synthesis","dataset":"InterHuman","model":"ComMDM","rank_in_archive_order":7,"of":10,"metrics":{"FID":"7.069","MMDist":"6.212","MModality":"1.822","R-Precision Top3":"0.466"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.01418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01418"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhenzhiwang/intercontrol","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/priormdm/priormdm","reach":null}],"summary":{"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"c9e52e6b3e54d9e1","entry":"calc_frame_colors","repo":"priormdm/priormdm","repo_kind":"official","path":"sample/double_take.py","file_url":"https://github.com/priormdm/priormdm/blob/HEAD/sample/double_take.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9e52e6b3e54d9e1"}},{"code_sha256_prefix":"0eba32186c812b63","entry":"evaluate_diversity","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0eba32186c812b63"}},{"code_sha256_prefix":"3d1767e9e020a4ee","entry":"evaluate_fid","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3d1767e9e020a4ee"}},{"code_sha256_prefix":"8b41dd559d056506","entry":"evaluate_matching_score","repo":"priormdm/priormdm","repo_kind":"official","path":"eval/eval_babel.py","file_url":"https://github.com/priormdm/priormdm/blob/HEAD/eval/eval_babel.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b41dd559d056506"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}