{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EOFHEGZMBLQZBHF4ZOUCGI6OYJ","short_pith_number":"pith:EOFHEGZM","schema_version":"1.0","canonical_sha256":"238a721b2c0ae1909cbccba82323cec247e6266b4d9aa73b088234cd32ed7d4c","source":{"kind":"arxiv","id":"2401.15977","version":2},"attestation_state":"computed","paper":{"title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dasong Li, Fu-Yun Wang, Hongsheng Li, Hongwei Qin, Jifeng Dai, Ka Chun Cheung, Manyuan Zhang, Simon See, Weikang Bian, Xiaoyu Shi, Yi Zhang, Zhaoyang Huang","submitted_at":"2024-01-29T09:06:43Z","abstract_excerpt":"We introduce Motion-I2V, a novel framework for consistent and controllable image-to-video generation (I2V). In contrast to previous methods that directly learn the complicated image-to-video mapping, Motion-I2V factorizes I2V into two stages with explicit motion modeling. For the first stage, we propose a diffusion-based motion field predictor, which focuses on deducing the trajectories of the reference image's pixels. For the second stage, we propose motion-augmented temporal attention to enhance the limited 1-D temporal attention in video latent diffusion models. This module can effectively "},"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":"2401.15977","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T09:06:43Z","cross_cats_sorted":[],"title_canon_sha256":"52f7031cd6bf106cb994d5c46da3f7c3bcc3e2f7df0ec0596fd2a48af3395124","abstract_canon_sha256":"bc8b8202a0b9dd432dff44bd50e708464f6a894a66c34eb02bd4bb9108663ab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:34.700063Z","signature_b64":"AqOfDc34nwu1xf8WNe1LWBkbddBk31ctaA/QmMaZ8TDyoGiuctTLAnodQMCBXwaYiAz+uHnEx/HXL6LN8mIUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"238a721b2c0ae1909cbccba82323cec247e6266b4d9aa73b088234cd32ed7d4c","last_reissued_at":"2026-07-05T07:39:34.699614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:34.699614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dasong Li, Fu-Yun Wang, Hongsheng Li, Hongwei Qin, Jifeng Dai, Ka Chun Cheung, Manyuan Zhang, Simon See, Weikang Bian, Xiaoyu Shi, Yi Zhang, Zhaoyang Huang","submitted_at":"2024-01-29T09:06:43Z","abstract_excerpt":"We introduce Motion-I2V, a novel framework for consistent and controllable image-to-video generation (I2V). In contrast to previous methods that directly learn the complicated image-to-video mapping, Motion-I2V factorizes I2V into two stages with explicit motion modeling. For the first stage, we propose a diffusion-based motion field predictor, which focuses on deducing the trajectories of the reference image's pixels. For the second stage, we propose motion-augmented temporal attention to enhance the limited 1-D temporal attention in video latent diffusion models. This module can effectively "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15977","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/2401.15977/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":"2401.15977","created_at":"2026-07-05T07:39:34.699670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15977v2","created_at":"2026-07-05T07:39:34.699670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15977","created_at":"2026-07-05T07:39:34.699670+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOFHEGZMBLQZ","created_at":"2026-07-05T07:39:34.699670+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOFHEGZMBLQZBHF4","created_at":"2026-07-05T07:39:34.699670+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOFHEGZM","created_at":"2026-07-05T07:39:34.699670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2404.02101","citing_title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","ref_index":146,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ","json":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ.json","graph_json":"https://pith.science/api/pith-number/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/graph.json","events_json":"https://pith.science/api/pith-number/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/events.json","paper":"https://pith.science/paper/EOFHEGZM"},"agent_actions":{"view_html":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ","download_json":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ.json","view_paper":"https://pith.science/paper/EOFHEGZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15977&json=true","fetch_graph":"https://pith.science/api/pith-number/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/action/storage_attestation","attest_author":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/action/author_attestation","sign_citation":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/action/citation_signature","submit_replication":"https://pith.science/pith/EOFHEGZMBLQZBHF4ZOUCGI6OYJ/action/replication_record"}},"created_at":"2026-07-05T07:39:34.699670+00:00","updated_at":"2026-07-05T07:39:34.699670+00:00"}