{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VNJDVRFRB67VBPO32BHKNOLGZY","short_pith_number":"pith:VNJDVRFR","schema_version":"1.0","canonical_sha256":"ab523ac4b10fbf50bddbd04ea6b966ce3bd142a84bffa3b832e0a829200b1b60","source":{"kind":"arxiv","id":"2508.08588","version":1},"attestation_state":"computed","paper":{"title":"RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chenjie Cao, Fan Wang, Jingkai Zhou, Jingyun Liang, Lei Sun, Shikai Li, Weihua Chen, Yichen Qian","submitted_at":"2025-08-12T03:02:23Z","abstract_excerpt":"Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background video, human trajectory and action patterns. In this paper, we propose a decomposed human motion control and video generation framework that explicitly decouples motion from appearance, subject from background, and action from trajectory, enabling flexible mix-and-match composition of these elements. Concretely, we first build a ground-aware 3D world coordina"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.08588","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-12T03:02:23Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"84f6083b5a60ee9fede12853279c7239d9dd56eb133584023bc5ec770e6476c5","abstract_canon_sha256":"7ff8cdcdcce86757942e67e4973a5ef70150c536e1390038979e663bcbb8e3e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:30.892920Z","signature_b64":"eoB6xrF2cWYScGrUsI9FnaD7lPC3Uogq+gfnncnSzROEMeSKpeLTHldvpFETFtFGkRKtFuqsDeJmKF0GY7tXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab523ac4b10fbf50bddbd04ea6b966ce3bd142a84bffa3b832e0a829200b1b60","last_reissued_at":"2026-07-05T11:52:30.892441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:30.892441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RealisMotion: Decomposed Human Motion Control and Video Generation in the World Space","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chenjie Cao, Fan Wang, Jingkai Zhou, Jingyun Liang, Lei Sun, Shikai Li, Weihua Chen, Yichen Qian","submitted_at":"2025-08-12T03:02:23Z","abstract_excerpt":"Generating human videos with realistic and controllable motions is a challenging task. While existing methods can generate visually compelling videos, they lack separate control over four key video elements: foreground subject, background video, human trajectory and action patterns. In this paper, we propose a decomposed human motion control and video generation framework that explicitly decouples motion from appearance, subject from background, and action from trajectory, enabling flexible mix-and-match composition of these elements. Concretely, we first build a ground-aware 3D world coordina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08588","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.08588/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.08588","created_at":"2026-07-05T11:52:30.892497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08588v1","created_at":"2026-07-05T11:52:30.892497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08588","created_at":"2026-07-05T11:52:30.892497+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNJDVRFRB67V","created_at":"2026-07-05T11:52:30.892497+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNJDVRFRB67VBPO3","created_at":"2026-07-05T11:52:30.892497+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNJDVRFR","created_at":"2026-07-05T11:52:30.892497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30514","citing_title":"3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02000","citing_title":"Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30514","citing_title":"3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10632","citing_title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY","json":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY.json","graph_json":"https://pith.science/api/pith-number/VNJDVRFRB67VBPO32BHKNOLGZY/graph.json","events_json":"https://pith.science/api/pith-number/VNJDVRFRB67VBPO32BHKNOLGZY/events.json","paper":"https://pith.science/paper/VNJDVRFR"},"agent_actions":{"view_html":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY","download_json":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY.json","view_paper":"https://pith.science/paper/VNJDVRFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08588&json=true","fetch_graph":"https://pith.science/api/pith-number/VNJDVRFRB67VBPO32BHKNOLGZY/graph.json","fetch_events":"https://pith.science/api/pith-number/VNJDVRFRB67VBPO32BHKNOLGZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY/action/storage_attestation","attest_author":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY/action/author_attestation","sign_citation":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY/action/citation_signature","submit_replication":"https://pith.science/pith/VNJDVRFRB67VBPO32BHKNOLGZY/action/replication_record"}},"created_at":"2026-07-05T11:52:30.892497+00:00","updated_at":"2026-07-05T11:52:30.892497+00:00"}