{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RXVKWLEQWXO53GABZHVI3IVH7J","short_pith_number":"pith:RXVKWLEQ","schema_version":"1.0","canonical_sha256":"8deaab2c90b5dddd9801c9ea8da2a7fa5cfea30bc608bb0165aabcaae3b5bfe2","source":{"kind":"arxiv","id":"2312.04875","version":3},"attestation_state":"computed","paper":{"title":"MVDD: Multi-View Depth Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achuta Kadambi, Feitong Tan, Menglei Chai, Qiangeng Xu, Rohit Pandey, Sean Fanello, Shichen Liu, Yinda Zhang, Zhen Wang","submitted_at":"2023-12-08T07:16:09Z","abstract_excerpt":"Denoising diffusion models have demonstrated outstanding results in 2D image generation, yet it remains a challenge to replicate its success in 3D shape generation. In this paper, we propose leveraging multi-view depth, which represents complex 3D shapes in a 2D data format that is easy to denoise. We pair this representation with a diffusion model, MVDD, that is capable of generating high-quality dense point clouds with 20K+ points with fine-grained details. To enforce 3D consistency in multi-view depth, we introduce an epipolar line segment attention that conditions the denoising step for a "},"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":"2312.04875","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-08T07:16:09Z","cross_cats_sorted":[],"title_canon_sha256":"87fa85f66449cc2065efc059695e43045988f5a8e19e95d576d0f91af11f4e30","abstract_canon_sha256":"9b0c28d86955a02964568a149bbbfe15e640522e4b4967c5b1b3cf5d2371904e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:19.360460Z","signature_b64":"vPGF+ED26ejRAOXC9o4rgo9oeYabomrc0SPgMSQ9BUd2AaTF3qZRZg39uEBWh9pqU+cFjE8JFyZQQCpUgon9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8deaab2c90b5dddd9801c9ea8da2a7fa5cfea30bc608bb0165aabcaae3b5bfe2","last_reissued_at":"2026-07-05T07:26:19.358721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:19.358721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVDD: Multi-View Depth Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achuta Kadambi, Feitong Tan, Menglei Chai, Qiangeng Xu, Rohit Pandey, Sean Fanello, Shichen Liu, Yinda Zhang, Zhen Wang","submitted_at":"2023-12-08T07:16:09Z","abstract_excerpt":"Denoising diffusion models have demonstrated outstanding results in 2D image generation, yet it remains a challenge to replicate its success in 3D shape generation. In this paper, we propose leveraging multi-view depth, which represents complex 3D shapes in a 2D data format that is easy to denoise. We pair this representation with a diffusion model, MVDD, that is capable of generating high-quality dense point clouds with 20K+ points with fine-grained details. To enforce 3D consistency in multi-view depth, we introduce an epipolar line segment attention that conditions the denoising step for a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04875","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/2312.04875/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":"2312.04875","created_at":"2026-07-05T07:26:19.358780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04875v3","created_at":"2026-07-05T07:26:19.358780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04875","created_at":"2026-07-05T07:26:19.358780+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXVKWLEQWXO5","created_at":"2026-07-05T07:26:19.358780+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXVKWLEQWXO53GAB","created_at":"2026-07-05T07:26:19.358780+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXVKWLEQ","created_at":"2026-07-05T07:26:19.358780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10947","citing_title":"Direct and Explicit 3D Generation from a Single Image","ref_index":86,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J","json":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J.json","graph_json":"https://pith.science/api/pith-number/RXVKWLEQWXO53GABZHVI3IVH7J/graph.json","events_json":"https://pith.science/api/pith-number/RXVKWLEQWXO53GABZHVI3IVH7J/events.json","paper":"https://pith.science/paper/RXVKWLEQ"},"agent_actions":{"view_html":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J","download_json":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J.json","view_paper":"https://pith.science/paper/RXVKWLEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04875&json=true","fetch_graph":"https://pith.science/api/pith-number/RXVKWLEQWXO53GABZHVI3IVH7J/graph.json","fetch_events":"https://pith.science/api/pith-number/RXVKWLEQWXO53GABZHVI3IVH7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J/action/storage_attestation","attest_author":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J/action/author_attestation","sign_citation":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J/action/citation_signature","submit_replication":"https://pith.science/pith/RXVKWLEQWXO53GABZHVI3IVH7J/action/replication_record"}},"created_at":"2026-07-05T07:26:19.358780+00:00","updated_at":"2026-07-05T07:26:19.358780+00:00"}