{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2XACAJKJ7WSGQNVC2OMJL7MGCD","short_pith_number":"pith:2XACAJKJ","schema_version":"1.0","canonical_sha256":"d5c0202549fda46836a2d39895fd8610dd3c0f34b0945ad45ae2c2761af05cb3","source":{"kind":"arxiv","id":"2311.17117","version":3},"attestation_state":"computed","paper":{"title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Ke Sun, Liefeng Bo, Li Hu, Peng Zhang, Xin Gao","submitted_at":"2023-11-28T12:27:15Z","abstract_excerpt":"Character Animation aims to generating character videos from still images through driving signals. Currently, diffusion models have become the mainstream in visual generation research, owing to their robust generative capabilities. However, challenges persist in the realm of image-to-video, especially in character animation, where temporally maintaining consistency with detailed information from character remains a formidable problem. In this paper, we leverage the power of diffusion models and propose a novel framework tailored for character animation. To preserve consistency of intricate app"},"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":"2311.17117","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T12:27:15Z","cross_cats_sorted":[],"title_canon_sha256":"aa0c9def3205abd29eb5694f1c38332cc0ea5b71abff31474f7d05d990d2c199","abstract_canon_sha256":"a26fbf2c4b304e6ad7b18576f923511082a899ce3ea62cd16e1486ba504e747e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:09.466686Z","signature_b64":"2ayRHbZqV23WB33dXeBW9rbMCh/2++sfMkRQZhSFWeLvm3pyctCStai2vleAJb3Yuot0+n5FvBRU8tyEf0rJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5c0202549fda46836a2d39895fd8610dd3c0f34b0945ad45ae2c2761af05cb3","last_reissued_at":"2026-07-05T08:31:09.466188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:09.466188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Ke Sun, Liefeng Bo, Li Hu, Peng Zhang, Xin Gao","submitted_at":"2023-11-28T12:27:15Z","abstract_excerpt":"Character Animation aims to generating character videos from still images through driving signals. Currently, diffusion models have become the mainstream in visual generation research, owing to their robust generative capabilities. However, challenges persist in the realm of image-to-video, especially in character animation, where temporally maintaining consistency with detailed information from character remains a formidable problem. In this paper, we leverage the power of diffusion models and propose a novel framework tailored for character animation. To preserve consistency of intricate app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17117","kind":"arxiv","version":3},"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/2311.17117/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":"2311.17117","created_at":"2026-07-05T08:31:09.466246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17117v3","created_at":"2026-07-05T08:31:09.466246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17117","created_at":"2026-07-05T08:31:09.466246+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XACAJKJ7WSG","created_at":"2026-07-05T08:31:09.466246+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XACAJKJ7WSGQNVC","created_at":"2026-07-05T08:31:09.466246+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XACAJKJ","created_at":"2026-07-05T08:31:09.466246+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27354","citing_title":"Error-Conditioned Neural Solvers","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02075","citing_title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","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":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15042","citing_title":"EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30514","citing_title":"3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16042","citing_title":"Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18576","citing_title":"DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21431","citing_title":"iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23279","citing_title":"Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09112","citing_title":"GimbalDiffusion: Gravity-Aware Camera Control for Video Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22160","citing_title":"Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13669","citing_title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17177","citing_title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12198","citing_title":"Enhancing Domain Generalization in 3D Human Pose Estimation through Controllable Generative Augmentation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10466","citing_title":"ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD","json":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD.json","graph_json":"https://pith.science/api/pith-number/2XACAJKJ7WSGQNVC2OMJL7MGCD/graph.json","events_json":"https://pith.science/api/pith-number/2XACAJKJ7WSGQNVC2OMJL7MGCD/events.json","paper":"https://pith.science/paper/2XACAJKJ"},"agent_actions":{"view_html":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD","download_json":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD.json","view_paper":"https://pith.science/paper/2XACAJKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17117&json=true","fetch_graph":"https://pith.science/api/pith-number/2XACAJKJ7WSGQNVC2OMJL7MGCD/graph.json","fetch_events":"https://pith.science/api/pith-number/2XACAJKJ7WSGQNVC2OMJL7MGCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD/action/storage_attestation","attest_author":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD/action/author_attestation","sign_citation":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD/action/citation_signature","submit_replication":"https://pith.science/pith/2XACAJKJ7WSGQNVC2OMJL7MGCD/action/replication_record"}},"created_at":"2026-07-05T08:31:09.466246+00:00","updated_at":"2026-07-05T08:31:09.466246+00:00"}