{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QX77AURYJKXWETQM72ZHDMZ3CR","short_pith_number":"pith:QX77AURY","schema_version":"1.0","canonical_sha256":"85fff052384aaf624e0cfeb271b33b14679bc02b2a144f278b67d2ac3125a6a2","source":{"kind":"arxiv","id":"2402.04324","version":2},"attestation_state":"computed","paper":{"title":"ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wei, Ge Zhang, Huan Yang, Weiming Ren, Wenhao Huang, Wenhu Chen, Xinrun Du","submitted_at":"2024-02-06T19:08:18Z","abstract_excerpt":"Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consistency throughout the video: existing methods often struggle to preserve the integrity of the subject, background, and style from the first frame, as well as ensure a fluid and logical progression within the video narrative. To mitigate these issues, we propose ConsistI2V, a diffusion-based method to enhance visual consistency for I2V generation. Specifically, we introduce (1) spatiotemporal attention over the first f"},"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":"2402.04324","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T19:08:18Z","cross_cats_sorted":[],"title_canon_sha256":"ef73612f2fe36cf070955695b2bd98177c9786a14ed11c7b3bd1a81a6ec87ba6","abstract_canon_sha256":"3dd0d98e3c1e90ce186f703400b2dac663880fde686900bbee43199fd6a9e964"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:05.906716Z","signature_b64":"J3a2U4+IL0V5ZlPrjgHOW6C7McBS+v847ixvjRmrhgZsXeRKvlD639MRKOx+MbO2uxF4m2OO9SRw522f+vKVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85fff052384aaf624e0cfeb271b33b14679bc02b2a144f278b67d2ac3125a6a2","last_reissued_at":"2026-07-05T08:38:05.906134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:05.906134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Wei, Ge Zhang, Huan Yang, Weiming Ren, Wenhao Huang, Wenhu Chen, Xinrun Du","submitted_at":"2024-02-06T19:08:18Z","abstract_excerpt":"Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consistency throughout the video: existing methods often struggle to preserve the integrity of the subject, background, and style from the first frame, as well as ensure a fluid and logical progression within the video narrative. To mitigate these issues, we propose ConsistI2V, a diffusion-based method to enhance visual consistency for I2V generation. Specifically, we introduce (1) spatiotemporal attention over the first f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04324","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/2402.04324/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":"2402.04324","created_at":"2026-07-05T08:38:05.906196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04324v2","created_at":"2026-07-05T08:38:05.906196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04324","created_at":"2026-07-05T08:38:05.906196+00:00"},{"alias_kind":"pith_short_12","alias_value":"QX77AURYJKXW","created_at":"2026-07-05T08:38:05.906196+00:00"},{"alias_kind":"pith_short_16","alias_value":"QX77AURYJKXWETQM","created_at":"2026-07-05T08:38:05.906196+00:00"},{"alias_kind":"pith_short_8","alias_value":"QX77AURY","created_at":"2026-07-05T08:38:05.906196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06309","citing_title":"RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01556","citing_title":"TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14843","citing_title":"MechVerse: Evaluating Physical Motion Consistency in Video Generation Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11723","citing_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14988","citing_title":"Compositional Video Generation via Inference-Time Guidance","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24674","citing_title":"Reasoning to Align: Implicit Reasoning in Diffusion Transformers for Video Editing","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01481","citing_title":"SafeGen-Bench: Benchmarking Safety in Image-Conditioned Text-to-Video Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23245","citing_title":"SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11723","citing_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25819","citing_title":"Mutual Forcing: Dual-Mode Self-Evolution for Fast Autoregressive Audio-Video Character Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2501.03575","citing_title":"Cosmos World Foundation Model Platform for Physical AI","ref_index":165,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR","json":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR.json","graph_json":"https://pith.science/api/pith-number/QX77AURYJKXWETQM72ZHDMZ3CR/graph.json","events_json":"https://pith.science/api/pith-number/QX77AURYJKXWETQM72ZHDMZ3CR/events.json","paper":"https://pith.science/paper/QX77AURY"},"agent_actions":{"view_html":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR","download_json":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR.json","view_paper":"https://pith.science/paper/QX77AURY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04324&json=true","fetch_graph":"https://pith.science/api/pith-number/QX77AURYJKXWETQM72ZHDMZ3CR/graph.json","fetch_events":"https://pith.science/api/pith-number/QX77AURYJKXWETQM72ZHDMZ3CR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR/action/storage_attestation","attest_author":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR/action/author_attestation","sign_citation":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR/action/citation_signature","submit_replication":"https://pith.science/pith/QX77AURYJKXWETQM72ZHDMZ3CR/action/replication_record"}},"created_at":"2026-07-05T08:38:05.906196+00:00","updated_at":"2026-07-05T08:38:05.906196+00:00"}