{"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/modi-unconditional-motion-synthesis-from","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","arxiv_id":"2206.08010","date":"2022-06-16","proceeding":"CVPR 2023 1","authors":["Sigal Raab","Inbal Leibovitch","Peizhuo Li","Kfir Aberman","Olga Sorkine-Hornung","Daniel Cohen-Or"],"abstract":"The emergence of neural networks has revolutionized the field of motion synthesis. Yet, learning to unconditionally synthesize motions from a given distribution remains challenging, especially when the motions are highly diverse. In this work, we present MoDi -- a generative model trained in an unsupervised setting from an extremely diverse, unstructured and unlabeled dataset. During inference, MoDi can synthesize high-quality, diverse motions. Despite the lack of any structure in the dataset, our model yields a well-behaved and highly structured latent space, which can be semantically clustered, constituting a strong motion prior that facilitates various applications including semantic editing and crowd simulation. In addition, we present an encoder that inverts real motions into MoDi's natural motion manifold, issuing solutions to various ill-posed challenges such as completion from prefix and spatial editing. Our qualitative and quantitative experiments achieve state-of-the-art results that outperform recent SOTA techniques. Code and trained models are available at https://sigal-raab.github.io/MoDi.","url_abs":"https://arxiv.org/abs/2206.08010v3","url_pdf":"https://arxiv.org/pdf/2206.08010v3.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":"modi-unconditional-motion-synthesis-from","repo_url":"https://github.com/sigal-raab/modi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"motion-interpolation","task_name":"Motion Interpolation"},{"task_slug":"motion-synthesis","task_name":"Motion Synthesis"}],"methods":[{"method_slug":"adaptive-instance-normalization","method_name":"Adaptive Instance Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"r1-regularization","method_name":"R1 Regularization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.08010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08010"}},"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/sigal-raab/modi","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"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":0,"samples":[{"code_sha256_prefix":"eb3bb72cda478b53","entry":"calculate_activation_statistics","repo":"sigal-raab/modi","repo_kind":"official","path":"evaluate.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/evaluate.py","link_basis":"harvester_set","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":"eb3bb72cda478b53"}},{"code_sha256_prefix":"cf180891b7a27bca","entry":"eval_input","repo":"sigal-raab/modi","repo_kind":"official","path":"generate_encoder.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/generate_encoder.py","link_basis":"harvester_set","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":"cf180891b7a27bca"}},{"code_sha256_prefix":"41d38a1e22220a87","entry":"inject_with_latent","repo":"sigal-raab/modi","repo_kind":"official","path":"generate_encoder.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/generate_encoder.py","link_basis":"harvester_set","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":"41d38a1e22220a87"}},{"code_sha256_prefix":"a51c35bf47a4e0dc","entry":"keep_skeletal_dims","repo":"sigal-raab/modi","repo_kind":"official","path":"models/gan.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/models/gan.py","link_basis":"harvester_set","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":"a51c35bf47a4e0dc"}},{"code_sha256_prefix":"b73f1b6f420da482","entry":"make_kernel","repo":"sigal-raab/modi","repo_kind":"official","path":"models/gan.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/models/gan.py","link_basis":"harvester_set","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":"b73f1b6f420da482"}},{"code_sha256_prefix":"947e1b49a8d0fc68","entry":"plot","repo":"sigal-raab/modi","repo_kind":"official","path":"motion_class.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/motion_class.py","link_basis":"harvester_set","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":"947e1b49a8d0fc68"}},{"code_sha256_prefix":"b451036e5d1a5894","entry":"prepare_recorder","repo":"sigal-raab/modi","repo_kind":"official","path":"train_encoder.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/train_encoder.py","link_basis":"harvester_set","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":"b451036e5d1a5894"}},{"code_sha256_prefix":"c79d6b3f30a6491c","entry":"r_wrist_vert_score","repo":"sigal-raab/modi","repo_kind":"official","path":"latent_space_edit.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/latent_space_edit.py","link_basis":"harvester_set","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":"c79d6b3f30a6491c"}},{"code_sha256_prefix":"a606b20b5a6e8820","entry":"sigmoid_for_contact","repo":"sigal-raab/modi","repo_kind":"official","path":"models/encoder_mask.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/models/encoder_mask.py","link_basis":"harvester_set","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":"a606b20b5a6e8820"}},{"code_sha256_prefix":"22fe9c52b1ab0dae","entry":"verticality_score","repo":"sigal-raab/modi","repo_kind":"official","path":"latent_space_edit.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/latent_space_edit.py","link_basis":"harvester_set","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":"22fe9c52b1ab0dae"}},{"code_sha256_prefix":"4bf8ccf16957cd51","entry":"z_from_seed","repo":"sigal-raab/modi","repo_kind":"official","path":"generate.py","file_url":"https://github.com/sigal-raab/modi/blob/HEAD/generate.py","link_basis":"harvester_set","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":"4bf8ccf16957cd51"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}