{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4OMAOM4MMCWAXKAINEYWSWJHKV","short_pith_number":"pith:4OMAOM4M","schema_version":"1.0","canonical_sha256":"e39807338c60ac0ba80869316959275552cc7580d56da4f36f493299de1e103a","source":{"kind":"arxiv","id":"2311.09217","version":1},"attestation_state":"computed","paper":{"title":"DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Gordon Wetzstein, Hao Tan, Jiahao Li, Kai Zhang, Kalyan Sunkavalli, Peng Wang, Sai Bi, Yinghao Xu, Zexiang Xu, Zifan Shi","submitted_at":"2023-11-15T18:58:41Z","abstract_excerpt":"We propose \\textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion. Our reconstruction model incorporates a triplane NeRF representation and can denoise noisy multi-view images via NeRF reconstruction and rendering, achieving single-stage 3D generation in $\\sim$30s on single A100 GPU. We train \\textbf{DMV3D} on large-scale multi-view image datasets of highly diverse objects using only image reconstruction losses, without accessing 3D assets. We demonstrate state-of-the-art results for the single-image reconstruc"},"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":"2311.09217","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-15T18:58:41Z","cross_cats_sorted":[],"title_canon_sha256":"ea31f260eddbac454a732829e6a59b17db100aabae3247937e1ee3f6dc04a78e","abstract_canon_sha256":"e626085b82045348f13fc20513afd55d83d7f65129df1bd9317f990f842ef02b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:10.350513Z","signature_b64":"uipJItq74dHr1uOPwjgAEGs7J7wP11cyvTzON83L+M7pwreZoWO77Dm/yGuzgO2SR3fJYcF3vaPZHnC9jI50Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e39807338c60ac0ba80869316959275552cc7580d56da4f36f493299de1e103a","last_reissued_at":"2026-07-05T07:13:10.349990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:10.349990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fujun Luan, Gordon Wetzstein, Hao Tan, Jiahao Li, Kai Zhang, Kalyan Sunkavalli, Peng Wang, Sai Bi, Yinghao Xu, Zexiang Xu, Zifan Shi","submitted_at":"2023-11-15T18:58:41Z","abstract_excerpt":"We propose \\textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion. Our reconstruction model incorporates a triplane NeRF representation and can denoise noisy multi-view images via NeRF reconstruction and rendering, achieving single-stage 3D generation in $\\sim$30s on single A100 GPU. We train \\textbf{DMV3D} on large-scale multi-view image datasets of highly diverse objects using only image reconstruction losses, without accessing 3D assets. We demonstrate state-of-the-art results for the single-image reconstruc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09217","kind":"arxiv","version":1},"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/2311.09217/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":"2311.09217","created_at":"2026-07-05T07:13:10.350052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09217v1","created_at":"2026-07-05T07:13:10.350052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09217","created_at":"2026-07-05T07:13:10.350052+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OMAOM4MMCWA","created_at":"2026-07-05T07:13:10.350052+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OMAOM4MMCWAXKAI","created_at":"2026-07-05T07:13:10.350052+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OMAOM4M","created_at":"2026-07-05T07:13:10.350052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.02316","citing_title":"ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":289,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16813","citing_title":"QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07435","citing_title":"DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.06608","citing_title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2403.02151","citing_title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV","json":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV.json","graph_json":"https://pith.science/api/pith-number/4OMAOM4MMCWAXKAINEYWSWJHKV/graph.json","events_json":"https://pith.science/api/pith-number/4OMAOM4MMCWAXKAINEYWSWJHKV/events.json","paper":"https://pith.science/paper/4OMAOM4M"},"agent_actions":{"view_html":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV","download_json":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV.json","view_paper":"https://pith.science/paper/4OMAOM4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09217&json=true","fetch_graph":"https://pith.science/api/pith-number/4OMAOM4MMCWAXKAINEYWSWJHKV/graph.json","fetch_events":"https://pith.science/api/pith-number/4OMAOM4MMCWAXKAINEYWSWJHKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV/action/storage_attestation","attest_author":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV/action/author_attestation","sign_citation":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV/action/citation_signature","submit_replication":"https://pith.science/pith/4OMAOM4MMCWAXKAINEYWSWJHKV/action/replication_record"}},"created_at":"2026-07-05T07:13:10.350052+00:00","updated_at":"2026-07-05T07:13:10.350052+00:00"}