{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZKFAS3DT5BH3EAK6TBV5DXEIZC","short_pith_number":"pith:ZKFAS3DT","schema_version":"1.0","canonical_sha256":"ca8a096c73e84fb2015e986bd1dc88c8b4fae506960894f7b271f05f1083eb5a","source":{"kind":"arxiv","id":"2406.15735","version":3},"attestation_state":"computed","paper":{"title":"Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chendong Xiang, Chongxuan Li, Hongzhou Zhu, Jun Zhu, Kaiwen Zheng, Min Zhao","submitted_at":"2024-06-22T04:56:16Z","abstract_excerpt":"Diffusion models have obtained substantial progress in image-to-video generation. However, in this paper, we find that these models tend to generate videos with less motion than expected. We attribute this to the issue called conditional image leakage, where the image-to-video diffusion models (I2V-DMs) tend to over-rely on the conditional image at large time steps. We further address this challenge from both inference and training aspects. First, we propose to start the generation process from an earlier time step to avoid the unreliable large-time steps of I2V-DMs, as well as an initial nois"},"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":"2406.15735","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-22T04:56:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"32564ce0ab82193b808de2eaafded5c7e40380bccd566e1ccf7edc156443a033","abstract_canon_sha256":"fb11575fc9735ce0d4a619801a7aa95b41878c1473f6f07a14d3250a11ad1f05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:46.993667Z","signature_b64":"fWPzX0AtB2m7ZaZcX4wbMscF0s1575r2VYdwSqwJZxUA8av1q36X7MGgdSsO8MCOsCfDduORyg/hnw4YE+COCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca8a096c73e84fb2015e986bd1dc88c8b4fae506960894f7b271f05f1083eb5a","last_reissued_at":"2026-07-05T09:31:46.993173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:46.993173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chendong Xiang, Chongxuan Li, Hongzhou Zhu, Jun Zhu, Kaiwen Zheng, Min Zhao","submitted_at":"2024-06-22T04:56:16Z","abstract_excerpt":"Diffusion models have obtained substantial progress in image-to-video generation. However, in this paper, we find that these models tend to generate videos with less motion than expected. We attribute this to the issue called conditional image leakage, where the image-to-video diffusion models (I2V-DMs) tend to over-rely on the conditional image at large time steps. We further address this challenge from both inference and training aspects. First, we propose to start the generation process from an earlier time step to avoid the unreliable large-time steps of I2V-DMs, as well as an initial nois"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15735","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/2406.15735/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":"2406.15735","created_at":"2026-07-05T09:31:46.993227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15735v3","created_at":"2026-07-05T09:31:46.993227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15735","created_at":"2026-07-05T09:31:46.993227+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKFAS3DT5BH3","created_at":"2026-07-05T09:31:46.993227+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKFAS3DT5BH3EAK6","created_at":"2026-07-05T09:31:46.993227+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKFAS3DT","created_at":"2026-07-05T09:31:46.993227+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07466","citing_title":"Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC","json":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC.json","graph_json":"https://pith.science/api/pith-number/ZKFAS3DT5BH3EAK6TBV5DXEIZC/graph.json","events_json":"https://pith.science/api/pith-number/ZKFAS3DT5BH3EAK6TBV5DXEIZC/events.json","paper":"https://pith.science/paper/ZKFAS3DT"},"agent_actions":{"view_html":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC","download_json":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC.json","view_paper":"https://pith.science/paper/ZKFAS3DT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15735&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKFAS3DT5BH3EAK6TBV5DXEIZC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKFAS3DT5BH3EAK6TBV5DXEIZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC/action/storage_attestation","attest_author":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC/action/author_attestation","sign_citation":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC/action/citation_signature","submit_replication":"https://pith.science/pith/ZKFAS3DT5BH3EAK6TBV5DXEIZC/action/replication_record"}},"created_at":"2026-07-05T09:31:46.993227+00:00","updated_at":"2026-07-05T09:31:46.993227+00:00"}