{"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/finemogen-fine-grained-spatio-temporal-motion-1","title":"FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing","arxiv_id":"2312.15004","date":"2023-12-22","proceeding":"NeurIPS 2023 11","authors":["Mingyuan Zhang","Huirong Li","Zhongang Cai","Jiawei Ren","Lei Yang","Ziwei Liu"],"abstract":"Text-driven motion generation has achieved substantial progress with the emergence of diffusion models. However, existing methods still struggle to generate complex motion sequences that correspond to fine-grained descriptions, depicting detailed and accurate spatio-temporal actions. This lack of fine controllability limits the usage of motion generation to a larger audience. To tackle these challenges, we present FineMoGen, a diffusion-based motion generation and editing framework that can synthesize fine-grained motions, with spatial-temporal composition to the user instructions. Specifically, FineMoGen builds upon diffusion model with a novel transformer architecture dubbed Spatio-Temporal Mixture Attention (SAMI). SAMI optimizes the generation of the global attention template from two perspectives: 1) explicitly modeling the constraints of spatio-temporal composition; and 2) utilizing sparsely-activated mixture-of-experts to adaptively extract fine-grained features. To facilitate a large-scale study on this new fine-grained motion generation task, we contribute the HuMMan-MoGen dataset, which consists of 2,968 videos and 102,336 fine-grained spatio-temporal descriptions. Extensive experiments validate that FineMoGen exhibits superior motion generation quality over state-of-the-art methods. Notably, FineMoGen further enables zero-shot motion editing capabilities with the aid of modern large language models (LLM), which faithfully manipulates motion sequences with fine-grained instructions. Project Page: https://mingyuan-zhang.github.io/projects/FineMoGen.html","url_abs":"https://arxiv.org/abs/2312.15004v1","url_pdf":"https://arxiv.org/pdf/2312.15004v1.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":"finemogen-fine-grained-spatio-temporal-motion-1","repo_url":"https://github.com/mingyuan-zhang/FineMoGen","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"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":"FineMoGen","rank_in_archive_order":24,"of":37,"metrics":{"Diversity":"9.263","FID":"0.151","Multimodality":"2.696","R Precision Top3":"0.784"},"uses_additional_data":false},{"leaderboard":"/sota/motion-synthesis-on-kit-motion-language","task":"Motion Synthesis","dataset":"KIT Motion-Language","model":"FineMoGen","rank_in_archive_order":6,"of":31,"metrics":{"Diversity":"10.85","FID":"0.178","Multimodality":"1.877","R Precision Top3":"0.772"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.15004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15004"}},"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/mingyuan-zhang/FineMoGen","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"ec92177c3f7ab4c1","entry":"get_kit_slice","repo":"mingyuan-zhang/FineMoGen","repo_kind":"official","path":"mogen/models/transformers/finemogen.py","file_url":"https://github.com/mingyuan-zhang/FineMoGen/blob/HEAD/mogen/models/transformers/finemogen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ec92177c3f7ab4c1"}},{"code_sha256_prefix":"e08b3bf468121672","entry":"get_part_slice","repo":"mingyuan-zhang/FineMoGen","repo_kind":"official","path":"mogen/models/transformers/finemogen.py","file_url":"https://github.com/mingyuan-zhang/FineMoGen/blob/HEAD/mogen/models/transformers/finemogen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e08b3bf468121672"}},{"code_sha256_prefix":"a8934e854740b364","entry":"get_t2m_slice","repo":"mingyuan-zhang/FineMoGen","repo_kind":"official","path":"mogen/models/transformers/finemogen.py","file_url":"https://github.com/mingyuan-zhang/FineMoGen/blob/HEAD/mogen/models/transformers/finemogen.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a8934e854740b364"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}