{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XYZA5R6V7WZWVBW36ZDNZZ4BKK","short_pith_number":"pith:XYZA5R6V","schema_version":"1.0","canonical_sha256":"be320ec7d5fdb36a86dbf646dce78152baaca804dd2205676330031f3013dc4e","source":{"kind":"arxiv","id":"2312.05133","version":2},"attestation_state":"computed","paper":{"title":"GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Zhou, Chenming Wu, Chen Zhao, Errui Ding, Haocheng Feng, Jian Zhang, Jingdong Wang, Xing Liu, Yahao Shi, Yanmin Wu","submitted_at":"2023-12-08T16:05:15Z","abstract_excerpt":"This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to effectively factorize the scene into material properties, light, and geometry. The key contributions lie in three-fold. We compute the normal of each 3D Gaussian using the shortest eigenvector, with a directional masking scheme forcing accurate normal estimation without external supervision. We adopt an efficient voxel-based indirect illumination tracing scheme that stores direction-aware outgoing radiance in each 3D Gaussian to disentangle secondary illumination for approximating multi-b"},"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":"2312.05133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-08T16:05:15Z","cross_cats_sorted":[],"title_canon_sha256":"66a787036bb554e1f9f8c1b2cd434cc188876dcb3b568dbf9566b943349f810f","abstract_canon_sha256":"1af68e6019f3e66fe41ae8230df613e121f27db2b930f7b4ce501c46528a152c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:32.579106Z","signature_b64":"5GU/79dLYqD+j2rkhYHuzyK5wXk2U7ZRAhWzq+Y51EaC5c2I0C7x+B9A0X0YQE3Jc47Dbc6XJY53fUaqI8m5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be320ec7d5fdb36a86dbf646dce78152baaca804dd2205676330031f3013dc4e","last_reissued_at":"2026-07-05T08:55:32.578532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:32.578532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Zhou, Chenming Wu, Chen Zhao, Errui Ding, Haocheng Feng, Jian Zhang, Jingdong Wang, Xing Liu, Yahao Shi, Yanmin Wu","submitted_at":"2023-12-08T16:05:15Z","abstract_excerpt":"This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to effectively factorize the scene into material properties, light, and geometry. The key contributions lie in three-fold. We compute the normal of each 3D Gaussian using the shortest eigenvector, with a directional masking scheme forcing accurate normal estimation without external supervision. We adopt an efficient voxel-based indirect illumination tracing scheme that stores direction-aware outgoing radiance in each 3D Gaussian to disentangle secondary illumination for approximating multi-b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05133","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/2312.05133/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":"2312.05133","created_at":"2026-07-05T08:55:32.578607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05133v2","created_at":"2026-07-05T08:55:32.578607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05133","created_at":"2026-07-05T08:55:32.578607+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYZA5R6V7WZW","created_at":"2026-07-05T08:55:32.578607+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYZA5R6V7WZWVBW3","created_at":"2026-07-05T08:55:32.578607+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYZA5R6V","created_at":"2026-07-05T08:55:32.578607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26007","citing_title":"From Sparse and Imperfect 2D Anchors to Consistent 3D Gaussian Street Scenes: Support-Aware Appearance","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25975","citing_title":"F-RNG: Feed-Forward Relightable Neural Gaussians","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05182","citing_title":"LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK","json":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK.json","graph_json":"https://pith.science/api/pith-number/XYZA5R6V7WZWVBW36ZDNZZ4BKK/graph.json","events_json":"https://pith.science/api/pith-number/XYZA5R6V7WZWVBW36ZDNZZ4BKK/events.json","paper":"https://pith.science/paper/XYZA5R6V"},"agent_actions":{"view_html":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK","download_json":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK.json","view_paper":"https://pith.science/paper/XYZA5R6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05133&json=true","fetch_graph":"https://pith.science/api/pith-number/XYZA5R6V7WZWVBW36ZDNZZ4BKK/graph.json","fetch_events":"https://pith.science/api/pith-number/XYZA5R6V7WZWVBW36ZDNZZ4BKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK/action/storage_attestation","attest_author":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK/action/author_attestation","sign_citation":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK/action/citation_signature","submit_replication":"https://pith.science/pith/XYZA5R6V7WZWVBW36ZDNZZ4BKK/action/replication_record"}},"created_at":"2026-07-05T08:55:32.578607+00:00","updated_at":"2026-07-05T08:55:32.578607+00:00"}