{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DK5JLS52E2R57ZUEL64HVJYBQO","short_pith_number":"pith:DK5JLS52","schema_version":"1.0","canonical_sha256":"1aba95cbba26a3dfe6845fb87aa70183b384275d87b912e81285805634131908","source":{"kind":"arxiv","id":"2412.18565","version":2},"attestation_state":"computed","paper":{"title":"3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Shangchen Zhou, Xingang Pan, Yihang Luo, Yushi Lan","submitted_at":"2024-12-24T17:36:34Z","abstract_excerpt":"Despite advances in neural rendering, due to the scarcity of high-quality 3D datasets and the inherent limitations of multi-view diffusion models, view synthesis and 3D model generation are restricted to low resolutions with suboptimal multi-view consistency. In this study, we present a novel 3D enhancement pipeline, dubbed 3DEnhancer, which employs a multi-view latent diffusion model to enhance coarse 3D inputs while preserving multi-view consistency. Our method includes a pose-aware encoder and a diffusion-based denoiser to refine low-quality multi-view images, along with data augmentation 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":"2412.18565","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T17:36:34Z","cross_cats_sorted":[],"title_canon_sha256":"005e578eb791fbf97b17a98f842fbdb1fff54ccb3e99a1831ad6c3cd9df3eb79","abstract_canon_sha256":"83c07c3b267cb692e0104512695a0f37145545267b113820845526976e337dca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:28.643774Z","signature_b64":"EDzyApzF+S+BQms1rdAINwMkgDmOkuems0vVFTfqSTEeBintXHTkcVy026J0p17e50SWJLVBpXHicksWdYvcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aba95cbba26a3dfe6845fb87aa70183b384275d87b912e81285805634131908","last_reissued_at":"2026-07-05T10:55:28.643277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:28.643277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Shangchen Zhou, Xingang Pan, Yihang Luo, Yushi Lan","submitted_at":"2024-12-24T17:36:34Z","abstract_excerpt":"Despite advances in neural rendering, due to the scarcity of high-quality 3D datasets and the inherent limitations of multi-view diffusion models, view synthesis and 3D model generation are restricted to low resolutions with suboptimal multi-view consistency. In this study, we present a novel 3D enhancement pipeline, dubbed 3DEnhancer, which employs a multi-view latent diffusion model to enhance coarse 3D inputs while preserving multi-view consistency. Our method includes a pose-aware encoder and a diffusion-based denoiser to refine low-quality multi-view images, along with data augmentation a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18565","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/2412.18565/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":"2412.18565","created_at":"2026-07-05T10:55:28.643331+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18565v2","created_at":"2026-07-05T10:55:28.643331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18565","created_at":"2026-07-05T10:55:28.643331+00:00"},{"alias_kind":"pith_short_12","alias_value":"DK5JLS52E2R5","created_at":"2026-07-05T10:55:28.643331+00:00"},{"alias_kind":"pith_short_16","alias_value":"DK5JLS52E2R57ZUE","created_at":"2026-07-05T10:55:28.643331+00:00"},{"alias_kind":"pith_short_8","alias_value":"DK5JLS52","created_at":"2026-07-05T10:55:28.643331+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00522","citing_title":"Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO","json":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO.json","graph_json":"https://pith.science/api/pith-number/DK5JLS52E2R57ZUEL64HVJYBQO/graph.json","events_json":"https://pith.science/api/pith-number/DK5JLS52E2R57ZUEL64HVJYBQO/events.json","paper":"https://pith.science/paper/DK5JLS52"},"agent_actions":{"view_html":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO","download_json":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO.json","view_paper":"https://pith.science/paper/DK5JLS52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18565&json=true","fetch_graph":"https://pith.science/api/pith-number/DK5JLS52E2R57ZUEL64HVJYBQO/graph.json","fetch_events":"https://pith.science/api/pith-number/DK5JLS52E2R57ZUEL64HVJYBQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO/action/storage_attestation","attest_author":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO/action/author_attestation","sign_citation":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO/action/citation_signature","submit_replication":"https://pith.science/pith/DK5JLS52E2R57ZUEL64HVJYBQO/action/replication_record"}},"created_at":"2026-07-05T10:55:28.643331+00:00","updated_at":"2026-07-05T10:55:28.643331+00:00"}