{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I3U22MHCZA6SDZAAFTWQBK4ZS6","short_pith_number":"pith:I3U22MHC","schema_version":"1.0","canonical_sha256":"46e9ad30e2c83d21e4002ced00ab99979ae4761e1e35228af6b64fd1495754a5","source":{"kind":"arxiv","id":"2311.12886","version":2},"attestation_state":"computed","paper":{"title":"AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingxue Qiu, Long Qin, Siyu Zhu, Weizhi Wang, Yao Yao, Zhenghao Zhang, Zuozhuo Dai","submitted_at":"2023-11-21T03:47:54Z","abstract_excerpt":"Image animation is a key task in computer vision which aims to generate dynamic visual content from static image. Recent image animation methods employ neural based rendering technique to generate realistic animations. Despite these advancements, achieving fine-grained and controllable image animation guided by text remains challenging, particularly for open-domain images captured in diverse real environments. In this paper, we introduce an open domain image animation method that leverages the motion prior of video diffusion model. Our approach introduces targeted motion area guidance and moti"},"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":"2311.12886","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-21T03:47:54Z","cross_cats_sorted":[],"title_canon_sha256":"7a423aa2f492b52de7f91a9b68867fd9d10fe246a810b378f8e254fdac3f0341","abstract_canon_sha256":"b092efd97d8203304246e93b140a68a38b60a81c27a9f2ca9f320016472435da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:12.578243Z","signature_b64":"SoPskR361r9dcVS5RxffKakj60ydPrF5rS+s0kTi49RWODHMfc81OAX5MyR4yIKf9Bs7ZUoN39yUDRjL0coTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46e9ad30e2c83d21e4002ced00ab99979ae4761e1e35228af6b64fd1495754a5","last_reissued_at":"2026-07-05T07:20:12.577875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:12.577875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingxue Qiu, Long Qin, Siyu Zhu, Weizhi Wang, Yao Yao, Zhenghao Zhang, Zuozhuo Dai","submitted_at":"2023-11-21T03:47:54Z","abstract_excerpt":"Image animation is a key task in computer vision which aims to generate dynamic visual content from static image. Recent image animation methods employ neural based rendering technique to generate realistic animations. Despite these advancements, achieving fine-grained and controllable image animation guided by text remains challenging, particularly for open-domain images captured in diverse real environments. In this paper, we introduce an open domain image animation method that leverages the motion prior of video diffusion model. Our approach introduces targeted motion area guidance and moti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.12886","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/2311.12886/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":"2311.12886","created_at":"2026-07-05T07:20:12.577928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.12886v2","created_at":"2026-07-05T07:20:12.577928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.12886","created_at":"2026-07-05T07:20:12.577928+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3U22MHCZA6S","created_at":"2026-07-05T07:20:12.577928+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3U22MHCZA6SDZAA","created_at":"2026-07-05T07:20:12.577928+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3U22MHC","created_at":"2026-07-05T07:20:12.577928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01869","citing_title":"QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17184","citing_title":"Substantial, Decomposable, and Invisible: Visual Context Misalignment in Instructional Videos for Physical Tasks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":226,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6","json":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6.json","graph_json":"https://pith.science/api/pith-number/I3U22MHCZA6SDZAAFTWQBK4ZS6/graph.json","events_json":"https://pith.science/api/pith-number/I3U22MHCZA6SDZAAFTWQBK4ZS6/events.json","paper":"https://pith.science/paper/I3U22MHC"},"agent_actions":{"view_html":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6","download_json":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6.json","view_paper":"https://pith.science/paper/I3U22MHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.12886&json=true","fetch_graph":"https://pith.science/api/pith-number/I3U22MHCZA6SDZAAFTWQBK4ZS6/graph.json","fetch_events":"https://pith.science/api/pith-number/I3U22MHCZA6SDZAAFTWQBK4ZS6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6/action/storage_attestation","attest_author":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6/action/author_attestation","sign_citation":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6/action/citation_signature","submit_replication":"https://pith.science/pith/I3U22MHCZA6SDZAAFTWQBK4ZS6/action/replication_record"}},"created_at":"2026-07-05T07:20:12.577928+00:00","updated_at":"2026-07-05T07:20:12.577928+00:00"}