{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7L4FNR6RZ6N6YECYR5QSVDZ7IX","short_pith_number":"pith:7L4FNR6R","schema_version":"1.0","canonical_sha256":"faf856c7d1cf9bec10588f612a8f3f45da6750335912c9810dfc39ef5c5c06e3","source":{"kind":"arxiv","id":"2501.03847","version":2},"attestation_state":"computed","paper":{"title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Cheng Lin, Chenyang Si, Jiahao Lu, Peng Li, Qifeng Liu, Rui Yan, Wenping Wang, Yuan Liu, Zekai Gu, Zhen Dong, Zhiyang Dou, Ziwei Liu","submitted_at":"2025-01-07T15:01:58Z","abstract_excerpt":"Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images. However, precise control over the video generation process, such as camera manipulation or content editing, remains a significant challenge. Existing methods for controlled video generation are typically limited to a single control type, lacking the flexibility to handle diverse control demands. In this paper, we introduce Diffusion as Shader (DaS), a novel approach that supports multiple video control tasks within a unified architecture. Our key insight is that achieving ve"},"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":"2501.03847","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-07T15:01:58Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"7169133da94eb12c3f065e66bfe6ee091ec4d398e2cc400f9730fcf6e934c78b","abstract_canon_sha256":"0a09d5837b9616fd889c599b27f8c5bb14c1b26eb328814b90ced51da10cc16d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:44.913410Z","signature_b64":"uWKfa6G51txhOApsruVT+7vR5/w6FyvP7vJjfNzynyMHE0y4fvZq7/FbNHcYHlVUOE9dSdILvKpW6eRK3Y9SCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faf856c7d1cf9bec10588f612a8f3f45da6750335912c9810dfc39ef5c5c06e3","last_reissued_at":"2026-07-05T09:58:44.912943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:44.912943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Cheng Lin, Chenyang Si, Jiahao Lu, Peng Li, Qifeng Liu, Rui Yan, Wenping Wang, Yuan Liu, Zekai Gu, Zhen Dong, Zhiyang Dou, Ziwei Liu","submitted_at":"2025-01-07T15:01:58Z","abstract_excerpt":"Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images. However, precise control over the video generation process, such as camera manipulation or content editing, remains a significant challenge. Existing methods for controlled video generation are typically limited to a single control type, lacking the flexibility to handle diverse control demands. In this paper, we introduce Diffusion as Shader (DaS), a novel approach that supports multiple video control tasks within a unified architecture. Our key insight is that achieving ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03847","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/2501.03847/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":"2501.03847","created_at":"2026-07-05T09:58:44.912999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03847v2","created_at":"2026-07-05T09:58:44.912999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03847","created_at":"2026-07-05T09:58:44.912999+00:00"},{"alias_kind":"pith_short_12","alias_value":"7L4FNR6RZ6N6","created_at":"2026-07-05T09:58:44.912999+00:00"},{"alias_kind":"pith_short_16","alias_value":"7L4FNR6RZ6N6YECY","created_at":"2026-07-05T09:58:44.912999+00:00"},{"alias_kind":"pith_short_8","alias_value":"7L4FNR6R","created_at":"2026-07-05T09:58:44.912999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18558","citing_title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09828","citing_title":"Latent Spatial Memory for Video World Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00499","citing_title":"OptiWorld: Optimal Control for Video World Generation under Physical Constraints","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22996","citing_title":"CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19741","citing_title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":224,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07209","citing_title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04911","citing_title":"SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX","json":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX.json","graph_json":"https://pith.science/api/pith-number/7L4FNR6RZ6N6YECYR5QSVDZ7IX/graph.json","events_json":"https://pith.science/api/pith-number/7L4FNR6RZ6N6YECYR5QSVDZ7IX/events.json","paper":"https://pith.science/paper/7L4FNR6R"},"agent_actions":{"view_html":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX","download_json":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX.json","view_paper":"https://pith.science/paper/7L4FNR6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03847&json=true","fetch_graph":"https://pith.science/api/pith-number/7L4FNR6RZ6N6YECYR5QSVDZ7IX/graph.json","fetch_events":"https://pith.science/api/pith-number/7L4FNR6RZ6N6YECYR5QSVDZ7IX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX/action/storage_attestation","attest_author":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX/action/author_attestation","sign_citation":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX/action/citation_signature","submit_replication":"https://pith.science/pith/7L4FNR6RZ6N6YECYR5QSVDZ7IX/action/replication_record"}},"created_at":"2026-07-05T09:58:44.912999+00:00","updated_at":"2026-07-05T09:58:44.912999+00:00"}