{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EYMLRAIZB6WVKESJHHJEJTMPST","short_pith_number":"pith:EYMLRAIZ","schema_version":"1.0","canonical_sha256":"2618b881190fad55124939d244cd8f94fa15dc8c15a52e8d85835f79254e65d5","source":{"kind":"arxiv","id":"2312.12274","version":2},"attestation_state":"computed","paper":{"title":"Intrinsic Image Diffusion for Indoor Single-view Material Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"(2) MIT EECS), Matthias Nie{\\ss}ner (1) ((1) Technical University of Munich, Peter Kocsis (1), Vincent Sitzmann (2)","submitted_at":"2023-12-19T15:56:19Z","abstract_excerpt":"We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material explanations represented as albedo, roughness, and metallic maps. Appearance decomposition poses a considerable challenge in computer vision due to the inherent ambiguity between lighting and material properties and the lack of real datasets. To address this issue, we advocate for a probabilistic formulation, where instead of attempting to directly predict the true material properties, we employ a conditional generative model to"},"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":"2312.12274","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T15:56:19Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"90214abd53c7af673f82e056531c3e1857b9d41379b68954c4af4ea0137afc62","abstract_canon_sha256":"ea49f8462d6f5832aeb8d5a09e548ba8fa389fb7b0cfb236aebb7fec20c88dac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:04.400012Z","signature_b64":"Y2smbZr+nQQ3eeHzOBsCZACBO2eXNc+7hsYiBx4cSODcl/P79uMd85M3yD6iYoAgmagSPpK5vgVMEPVaw+04Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2618b881190fad55124939d244cd8f94fa15dc8c15a52e8d85835f79254e65d5","last_reissued_at":"2026-07-05T07:59:04.399569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:04.399569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intrinsic Image Diffusion for Indoor Single-view Material Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"(2) MIT EECS), Matthias Nie{\\ss}ner (1) ((1) Technical University of Munich, Peter Kocsis (1), Vincent Sitzmann (2)","submitted_at":"2023-12-19T15:56:19Z","abstract_excerpt":"We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material explanations represented as albedo, roughness, and metallic maps. Appearance decomposition poses a considerable challenge in computer vision due to the inherent ambiguity between lighting and material properties and the lack of real datasets. To address this issue, we advocate for a probabilistic formulation, where instead of attempting to directly predict the true material properties, we employ a conditional generative model to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12274","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/2312.12274/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":"2312.12274","created_at":"2026-07-05T07:59:04.399627+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12274v2","created_at":"2026-07-05T07:59:04.399627+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12274","created_at":"2026-07-05T07:59:04.399627+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYMLRAIZB6WV","created_at":"2026-07-05T07:59:04.399627+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYMLRAIZB6WVKESJ","created_at":"2026-07-05T07:59:04.399627+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYMLRAIZ","created_at":"2026-07-05T07:59:04.399627+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.14461","citing_title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27871","citing_title":"D-Rex : Diffusion Rendering for Relightable Expressive Avatars","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST","json":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST.json","graph_json":"https://pith.science/api/pith-number/EYMLRAIZB6WVKESJHHJEJTMPST/graph.json","events_json":"https://pith.science/api/pith-number/EYMLRAIZB6WVKESJHHJEJTMPST/events.json","paper":"https://pith.science/paper/EYMLRAIZ"},"agent_actions":{"view_html":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST","download_json":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST.json","view_paper":"https://pith.science/paper/EYMLRAIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12274&json=true","fetch_graph":"https://pith.science/api/pith-number/EYMLRAIZB6WVKESJHHJEJTMPST/graph.json","fetch_events":"https://pith.science/api/pith-number/EYMLRAIZB6WVKESJHHJEJTMPST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST/action/storage_attestation","attest_author":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST/action/author_attestation","sign_citation":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST/action/citation_signature","submit_replication":"https://pith.science/pith/EYMLRAIZB6WVKESJHHJEJTMPST/action/replication_record"}},"created_at":"2026-07-05T07:59:04.399627+00:00","updated_at":"2026-07-05T07:59:04.399627+00:00"}