{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PY2BX2MGVNQHURSM77LMOGWH2Y","short_pith_number":"pith:PY2BX2MG","schema_version":"1.0","canonical_sha256":"7e341be986ab607a464cffd6c71ac7d61faef1a8cde1379c745ff49626ee4e3f","source":{"kind":"arxiv","id":"2304.11603","version":2},"attestation_state":"computed","paper":{"title":"LaMD: Latent Motion Diffusion for Image-Conditional Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Luo, Yaosi Hu, Zhenzhong Chen","submitted_at":"2023-04-23T10:32:32Z","abstract_excerpt":"The video generation field has witnessed rapid improvements with the introduction of recent diffusion models. While these models have successfully enhanced appearance quality, they still face challenges in generating coherent and natural movements while efficiently sampling videos. In this paper, we propose to condense video generation into a problem of motion generation, to improve the expressiveness of motion and make video generation more manageable. This can be achieved by breaking down the video generation process into latent motion generation and video reconstruction. Specifically, we pr"},"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":"2304.11603","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-23T10:32:32Z","cross_cats_sorted":[],"title_canon_sha256":"2039a7663898b26efcebed2864b6b1e38476f3ddd61b6f31e882ed1a479d569c","abstract_canon_sha256":"64be5575da7c08d8a563171ee7842ac77c803806e1f4a3671c3fba41f14bf581"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:40.206305Z","signature_b64":"+syzhpVC2lqviUW8aSk70BH2debJLPX2s/wH8zZz0e8qeC8xFba/ctK3PfWOKmo6njd5DvwphCMChrLHBaBDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e341be986ab607a464cffd6c71ac7d61faef1a8cde1379c745ff49626ee4e3f","last_reissued_at":"2026-07-05T10:50:40.205821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:40.205821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LaMD: Latent Motion Diffusion for Image-Conditional Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Luo, Yaosi Hu, Zhenzhong Chen","submitted_at":"2023-04-23T10:32:32Z","abstract_excerpt":"The video generation field has witnessed rapid improvements with the introduction of recent diffusion models. While these models have successfully enhanced appearance quality, they still face challenges in generating coherent and natural movements while efficiently sampling videos. In this paper, we propose to condense video generation into a problem of motion generation, to improve the expressiveness of motion and make video generation more manageable. This can be achieved by breaking down the video generation process into latent motion generation and video reconstruction. Specifically, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11603","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/2304.11603/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":"2304.11603","created_at":"2026-07-05T10:50:40.205882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11603v2","created_at":"2026-07-05T10:50:40.205882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11603","created_at":"2026-07-05T10:50:40.205882+00:00"},{"alias_kind":"pith_short_12","alias_value":"PY2BX2MGVNQH","created_at":"2026-07-05T10:50:40.205882+00:00"},{"alias_kind":"pith_short_16","alias_value":"PY2BX2MGVNQHURSM","created_at":"2026-07-05T10:50:40.205882+00:00"},{"alias_kind":"pith_short_8","alias_value":"PY2BX2MG","created_at":"2026-07-05T10:50:40.205882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.16748","citing_title":"Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2502.06431","citing_title":"FCVSR: A Frequency-aware Method for Compressed Video Super-Resolution","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02849","citing_title":"Active Sampling for Ultra-Low-Bit-Rate Video Compression via Conditional Controlled Diffusion","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y","json":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y.json","graph_json":"https://pith.science/api/pith-number/PY2BX2MGVNQHURSM77LMOGWH2Y/graph.json","events_json":"https://pith.science/api/pith-number/PY2BX2MGVNQHURSM77LMOGWH2Y/events.json","paper":"https://pith.science/paper/PY2BX2MG"},"agent_actions":{"view_html":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y","download_json":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y.json","view_paper":"https://pith.science/paper/PY2BX2MG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11603&json=true","fetch_graph":"https://pith.science/api/pith-number/PY2BX2MGVNQHURSM77LMOGWH2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/PY2BX2MGVNQHURSM77LMOGWH2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y/action/storage_attestation","attest_author":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y/action/author_attestation","sign_citation":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y/action/citation_signature","submit_replication":"https://pith.science/pith/PY2BX2MGVNQHURSM77LMOGWH2Y/action/replication_record"}},"created_at":"2026-07-05T10:50:40.205882+00:00","updated_at":"2026-07-05T10:50:40.205882+00:00"}