{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SQRY5AQWERI5EP365T7PRR7VQ2","short_pith_number":"pith:SQRY5AQW","schema_version":"1.0","canonical_sha256":"94238e82162451d23f7eecfef8c7f586a4c88b9d0670f4f95f420a92a5aaf2b0","source":{"kind":"arxiv","id":"2412.00177","version":3},"attestation_state":"computed","paper":{"title":"LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anand Bhattad, Konrad Groh, Sezer Karaoglu, Theo Gevers, Xiaoyan Xing","submitted_at":"2024-11-29T18:59:11Z","abstract_excerpt":"We introduce LumiNet, a novel architecture that leverages generative models and latent intrinsic representations for effective lighting transfer. Given a source image and a target lighting image, LumiNet synthesizes a relit version of the source scene that captures the target's lighting. Our approach makes two key contributions: a data curation strategy from the StyleGAN-based relighting model for our training, and a modified diffusion-based ControlNet that processes both latent intrinsic properties from the source image and latent extrinsic properties from the target image. We further improve"},"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":"2412.00177","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T18:59:11Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"bec48099118984af1ad0487dc8521f7f24e676696ba30e55730b8fbf2b618259","abstract_canon_sha256":"bc7ef6c0486a14f88d835e7a7aac71e5c9fd18924f81fc420fbdbc9168a8db0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:13.504455Z","signature_b64":"cLK2VU76VEgJtkj+l8cHIGlC92CaelGSxWfhCLVw2OWZGV/TLiJwOBnIzFZYgJ6s0n70uygwwALizkY72c+8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94238e82162451d23f7eecfef8c7f586a4c88b9d0670f4f95f420a92a5aaf2b0","last_reissued_at":"2026-07-05T12:04:13.503933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:13.503933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anand Bhattad, Konrad Groh, Sezer Karaoglu, Theo Gevers, Xiaoyan Xing","submitted_at":"2024-11-29T18:59:11Z","abstract_excerpt":"We introduce LumiNet, a novel architecture that leverages generative models and latent intrinsic representations for effective lighting transfer. Given a source image and a target lighting image, LumiNet synthesizes a relit version of the source scene that captures the target's lighting. Our approach makes two key contributions: a data curation strategy from the StyleGAN-based relighting model for our training, and a modified diffusion-based ControlNet that processes both latent intrinsic properties from the source image and latent extrinsic properties from the target image. We further improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00177","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/2412.00177/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":"2412.00177","created_at":"2026-07-05T12:04:13.503997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00177v3","created_at":"2026-07-05T12:04:13.503997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00177","created_at":"2026-07-05T12:04:13.503997+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQRY5AQWERI5","created_at":"2026-07-05T12:04:13.503997+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQRY5AQWERI5EP36","created_at":"2026-07-05T12:04:13.503997+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQRY5AQW","created_at":"2026-07-05T12:04:13.503997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11314","citing_title":"TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2","json":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2.json","graph_json":"https://pith.science/api/pith-number/SQRY5AQWERI5EP365T7PRR7VQ2/graph.json","events_json":"https://pith.science/api/pith-number/SQRY5AQWERI5EP365T7PRR7VQ2/events.json","paper":"https://pith.science/paper/SQRY5AQW"},"agent_actions":{"view_html":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2","download_json":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2.json","view_paper":"https://pith.science/paper/SQRY5AQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00177&json=true","fetch_graph":"https://pith.science/api/pith-number/SQRY5AQWERI5EP365T7PRR7VQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/SQRY5AQWERI5EP365T7PRR7VQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2/action/storage_attestation","attest_author":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2/action/author_attestation","sign_citation":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2/action/citation_signature","submit_replication":"https://pith.science/pith/SQRY5AQWERI5EP365T7PRR7VQ2/action/replication_record"}},"created_at":"2026-07-05T12:04:13.503997+00:00","updated_at":"2026-07-05T12:04:13.503997+00:00"}