{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QV36ZMKPRQPIBL5WH4L7IYUNKH","short_pith_number":"pith:QV36ZMKP","schema_version":"1.0","canonical_sha256":"8577ecb14f8c1e80afb63f17f4628d51e21e2196bce73d2a5f43a2bf04dda51e","source":{"kind":"arxiv","id":"2503.21246","version":2},"attestation_state":"computed","paper":{"title":"DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wang, Fei Chen, Guansong Lu, Hang Xu, Haoyu Zhao, Qingping Zheng, Zhongang Qi, Zuxuan Wu","submitted_at":"2025-03-27T08:07:45Z","abstract_excerpt":"With diffusion transformer (DiT) excelling in video generation, its use in specific tasks has drawn increasing attention. However, adapting DiT for pose-guided human image animation faces two core challenges: (a) existing U-Net-based pose control methods may be suboptimal for the DiT backbone; and (b) removing text guidance, as in previous approaches, often leads to semantic loss and model degradation. To address these issues, we propose DynamiCtrl, a novel framework for human animation in video DiT architecture. Specifically, we use a shared VAE encoder for human images and driving poses, uni"},"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":"2503.21246","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-27T08:07:45Z","cross_cats_sorted":[],"title_canon_sha256":"81885d72bc9c61c82e0700668b68a327381b4135af5ccbc58af8ad893ed6c41b","abstract_canon_sha256":"da4f8ba22d024608f69fb3015112ed1de585bb10decef9d7326a7ce2646ddb24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:47.950659Z","signature_b64":"h/7cC0Fy7pVmhZEo86jHPFUPYqS3VMxu+EctvygeqE1AITGtqHQEbxf3u2q9IYOGjx4Q6YhykO4Bkyax6B31Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8577ecb14f8c1e80afb63f17f4628d51e21e2196bce73d2a5f43a2bf04dda51e","last_reissued_at":"2026-07-05T11:04:47.950126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:47.950126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wang, Fei Chen, Guansong Lu, Hang Xu, Haoyu Zhao, Qingping Zheng, Zhongang Qi, Zuxuan Wu","submitted_at":"2025-03-27T08:07:45Z","abstract_excerpt":"With diffusion transformer (DiT) excelling in video generation, its use in specific tasks has drawn increasing attention. However, adapting DiT for pose-guided human image animation faces two core challenges: (a) existing U-Net-based pose control methods may be suboptimal for the DiT backbone; and (b) removing text guidance, as in previous approaches, often leads to semantic loss and model degradation. To address these issues, we propose DynamiCtrl, a novel framework for human animation in video DiT architecture. Specifically, we use a shared VAE encoder for human images and driving poses, uni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.21246","kind":"arxiv","version":2},"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/2503.21246/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":"2503.21246","created_at":"2026-07-05T11:04:47.950194+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.21246v2","created_at":"2026-07-05T11:04:47.950194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.21246","created_at":"2026-07-05T11:04:47.950194+00:00"},{"alias_kind":"pith_short_12","alias_value":"QV36ZMKPRQPI","created_at":"2026-07-05T11:04:47.950194+00:00"},{"alias_kind":"pith_short_16","alias_value":"QV36ZMKPRQPIBL5W","created_at":"2026-07-05T11:04:47.950194+00:00"},{"alias_kind":"pith_short_8","alias_value":"QV36ZMKP","created_at":"2026-07-05T11:04:47.950194+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06903","citing_title":"Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH","json":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH.json","graph_json":"https://pith.science/api/pith-number/QV36ZMKPRQPIBL5WH4L7IYUNKH/graph.json","events_json":"https://pith.science/api/pith-number/QV36ZMKPRQPIBL5WH4L7IYUNKH/events.json","paper":"https://pith.science/paper/QV36ZMKP"},"agent_actions":{"view_html":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH","download_json":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH.json","view_paper":"https://pith.science/paper/QV36ZMKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.21246&json=true","fetch_graph":"https://pith.science/api/pith-number/QV36ZMKPRQPIBL5WH4L7IYUNKH/graph.json","fetch_events":"https://pith.science/api/pith-number/QV36ZMKPRQPIBL5WH4L7IYUNKH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH/action/storage_attestation","attest_author":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH/action/author_attestation","sign_citation":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH/action/citation_signature","submit_replication":"https://pith.science/pith/QV36ZMKPRQPIBL5WH4L7IYUNKH/action/replication_record"}},"created_at":"2026-07-05T11:04:47.950194+00:00","updated_at":"2026-07-05T11:04:47.950194+00:00"}