{"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/simmotionedit-text-based-human-motion-editing","title":"SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction","arxiv_id":"2503.18211","date":"2025-03-23","proceeding":"CVPR 2025 1","authors":["Zhengyuan Li","Kai Cheng","Anindita Ghosh","Uttaran Bhattacharya","LiangYan Gui","Aniket Bera"],"abstract":"Text-based 3D human motion editing is a critical yet challenging task in computer vision and graphics. While training-free approaches have been explored, the recent release of the MotionFix dataset, which includes source-text-motion triplets, has opened new avenues for training, yielding promising results. However, existing methods struggle with precise control, often leading to misalignment between motion semantics and language instructions. In this paper, we introduce a related task, motion similarity prediction, and propose a multi-task training paradigm, where we train the model jointly on motion editing and motion similarity prediction to foster the learning of semantically meaningful representations. To complement this task, we design an advanced Diffusion-Transformer-based architecture that separately handles motion similarity prediction and motion editing. Extensive experiments demonstrate the state-of-the-art performance of our approach in both editing alignment and fidelity.","url_abs":"https://arxiv.org/abs/2503.18211v2","url_pdf":"https://arxiv.org/pdf/2503.18211v2.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":"simmotionedit-text-based-human-motion-editing","repo_url":"https://github.com/lzhyu/simmotionedit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.18211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18211"}},"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":"deterministic:regex_extraction","url":"https://github.com/lzhyu/SimMotionEdit","reach":null}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"72ebe95ffd10e9f6","entry":"Attention","repo":"lzhyu/SimMotionEdit","repo_kind":"official","path":"src/model/DiT_denoiser.py","file_url":"https://github.com/lzhyu/SimMotionEdit/blob/HEAD/src/model/DiT_denoiser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72ebe95ffd10e9f6"}},{"code_sha256_prefix":"944b47cdd8b8b291","entry":"PositionalEncoding","repo":"lzhyu/SimMotionEdit","repo_kind":"official","path":"src/model/DiT_denoiser.py","file_url":"https://github.com/lzhyu/SimMotionEdit/blob/HEAD/src/model/DiT_denoiser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"944b47cdd8b8b291"}},{"code_sha256_prefix":"ade6b33b87261cff","entry":"DiTBlock","repo":"lzhyu/SimMotionEdit","repo_kind":"official","path":"src/model/DiT_denoiser.py","file_url":"https://github.com/lzhyu/SimMotionEdit/blob/HEAD/src/model/DiT_denoiser.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":"ade6b33b87261cff"}},{"code_sha256_prefix":"c333b90239869981","entry":"DiTMotion","repo":"lzhyu/SimMotionEdit","repo_kind":"official","path":"src/model/DiT_denoiser.py","file_url":"https://github.com/lzhyu/SimMotionEdit/blob/HEAD/src/model/DiT_denoiser.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":"c333b90239869981"}},{"code_sha256_prefix":"c7705a7cb1b2a18e","entry":"DiT_Denoiser","repo":"lzhyu/SimMotionEdit","repo_kind":"official","path":"src/model/DiT_denoiser.py","file_url":"https://github.com/lzhyu/SimMotionEdit/blob/HEAD/src/model/DiT_denoiser.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":"c7705a7cb1b2a18e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}