{"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/emdm-efficient-motion-diffusion-model-for","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","arxiv_id":"2312.02256","date":"2023-12-04","proceeding":null,"authors":["Wenyang Zhou","Zhiyang Dou","Zeyu Cao","Zhouyingcheng Liao","Jingbo Wang","Wenjia Wang","YuAn Liu","Taku Komura","Wenping Wang","Lingjie Liu"],"abstract":"We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation. Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without sacrificing quality. On the one hand, previous works, like motion latent diffusion, conduct diffusion within a latent space for efficiency, but learning such a latent space can be a non-trivial effort. On the other hand, accelerating generation by naively increasing the sampling step size, e.g., DDIM, often leads to quality degradation as it fails to approximate the complex denoising distribution. To address these issues, we propose EMDM, which captures the complex distribution during multiple sampling steps in the diffusion model, allowing for much fewer sampling steps and significant acceleration in generation. This is achieved by a conditional denoising diffusion GAN to capture multimodal data distributions among arbitrary (and potentially larger) step sizes conditioned on control signals, enabling fewer-step motion sampling with high fidelity and diversity. To minimize undesired motion artifacts, geometric losses are imposed during network learning. As a result, EMDM achieves real-time motion generation and significantly improves the efficiency of motion diffusion models compared to existing methods while achieving high-quality motion generation. Our code will be publicly available upon publication.","url_abs":"https://arxiv.org/abs/2312.02256v3","url_pdf":"https://arxiv.org/pdf/2312.02256v3.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":"emdm-efficient-motion-diffusion-model-for","repo_url":"https://github.com/frank-zy-dou/emdm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"human-dynamics","task_name":"Human Dynamics"},{"task_slug":"motion-generation","task_name":"Motion Generation"},{"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-humanml3d","task":"Motion Synthesis","dataset":"HumanML3D","model":"EMDM","rank_in_archive_order":19,"of":37,"metrics":{"Diversity":"9.551","FID":"0.112","Multimodality":"1.641","R Precision Top3":"0.786"},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-kit-motion-language","task":"Motion Synthesis","dataset":"KIT Motion-Language","model":"EMDM","rank_in_archive_order":10,"of":31,"metrics":{"Diversity":"10.96","FID":"0.261","Multimodality":"1.343","R Precision Top3":"0.780"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.02256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02256"}},"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/frank-zy-dou/emdm","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":7,"samples":[{"code_sha256_prefix":"cfd76fd0d89574a4","entry":"approx_standard_normal_cdf","repo":"frank-zy-dou/emdm","repo_kind":"official","path":"diffusion/losses.py","file_url":"https://github.com/frank-zy-dou/emdm/blob/HEAD/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cfd76fd0d89574a4"}},{"code_sha256_prefix":"cd33283d615fb3d7","entry":"discretized_gaussian_log_likelihood","repo":"frank-zy-dou/emdm","repo_kind":"official","path":"diffusion/losses.py","file_url":"https://github.com/frank-zy-dou/emdm/blob/HEAD/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd33283d615fb3d7"}},{"code_sha256_prefix":"cf2798b666b231ca","entry":"normal_kl","repo":"frank-zy-dou/emdm","repo_kind":"official","path":"diffusion/losses.py","file_url":"https://github.com/frank-zy-dou/emdm/blob/HEAD/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cf2798b666b231ca"}},{"code_sha256_prefix":"0eba32186c812b63","entry":"evaluate_diversity","repo":"frank-zy-dou/emdm","repo_kind":"official","path":"eval_humanml.py","file_url":"https://github.com/frank-zy-dou/emdm/blob/HEAD/eval_humanml.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0eba32186c812b63"}},{"code_sha256_prefix":"6a6a115008da7ad3","entry":"evaluate_fid","repo":"frank-zy-dou/emdm","repo_kind":"official","path":"eval_humanml.py","file_url":"https://github.com/frank-zy-dou/emdm/blob/HEAD/eval_humanml.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a6a115008da7ad3"}},{"code_sha256_prefix":"0f0a2de622a554fe","entry":"evaluate_matching_score","repo":"frank-zy-dou/emdm","repo_kind":"official","path":"eval_humanml.py","file_url":"https://github.com/frank-zy-dou/emdm/blob/HEAD/eval_humanml.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f0a2de622a554fe"}},{"code_sha256_prefix":"ccb982718fc51057","entry":"get_metric_statistics","repo":"frank-zy-dou/emdm","repo_kind":"official","path":"eval_humanact12_uestc.py","file_url":"https://github.com/frank-zy-dou/emdm/blob/HEAD/eval_humanact12_uestc.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":"ccb982718fc51057"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}