{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BWL7QZRDBCMIYVVJIWEILVQMDC","short_pith_number":"pith:BWL7QZRD","schema_version":"1.0","canonical_sha256":"0d97f8662308988c56a9458885d60c1889ffec03461f22abf368c1a37c3e7837","source":{"kind":"arxiv","id":"2501.09756","version":1},"attestation_state":"computed","paper":{"title":"SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jingyuan Liu, Julie Dorsey, Mengwei Ren, Sumit Chaturvedi, Yannick Hold-Geoffroy, Zhixin Shu","submitted_at":"2025-01-16T18:59:48Z","abstract_excerpt":"We introduce SynthLight, a diffusion model for portrait relighting. Our approach frames image relighting as a re-rendering problem, where pixels are transformed in response to changes in environmental lighting conditions. Using a physically-based rendering engine, we synthesize a dataset to simulate this lighting-conditioned transformation with 3D head assets under varying lighting. We propose two training and inference strategies to bridge the gap between the synthetic and real image domains: (1) multi-task training that takes advantage of real human portraits without lighting labels; (2) an "},"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":"2501.09756","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-16T18:59:48Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"0590d7c0f7e5edb9f8db9194b9a9bc25d9aa13711678b0c8b04aa35d238f0555","abstract_canon_sha256":"ab2d19ff1e6e34491f1cd04cb79a8a4bd4a95be711ea59104929e49624e494ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:58.150091Z","signature_b64":"pHpqzW3GfpGr/swj9xk8X6sW2azblsHzz6/Uo++Zn30U1F9fYF6tbjDXrieTJ+a9R4HMCEfgskGB1PAA1FH1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d97f8662308988c56a9458885d60c1889ffec03461f22abf368c1a37c3e7837","last_reissued_at":"2026-07-05T10:01:58.149620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:58.149620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Jingyuan Liu, Julie Dorsey, Mengwei Ren, Sumit Chaturvedi, Yannick Hold-Geoffroy, Zhixin Shu","submitted_at":"2025-01-16T18:59:48Z","abstract_excerpt":"We introduce SynthLight, a diffusion model for portrait relighting. Our approach frames image relighting as a re-rendering problem, where pixels are transformed in response to changes in environmental lighting conditions. Using a physically-based rendering engine, we synthesize a dataset to simulate this lighting-conditioned transformation with 3D head assets under varying lighting. We propose two training and inference strategies to bridge the gap between the synthetic and real image domains: (1) multi-task training that takes advantage of real human portraits without lighting labels; (2) an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09756","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/2501.09756/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":"2501.09756","created_at":"2026-07-05T10:01:58.149671+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09756v1","created_at":"2026-07-05T10:01:58.149671+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09756","created_at":"2026-07-05T10:01:58.149671+00:00"},{"alias_kind":"pith_short_12","alias_value":"BWL7QZRDBCMI","created_at":"2026-07-05T10:01:58.149671+00:00"},{"alias_kind":"pith_short_16","alias_value":"BWL7QZRDBCMIYVVJ","created_at":"2026-07-05T10:01:58.149671+00:00"},{"alias_kind":"pith_short_8","alias_value":"BWL7QZRD","created_at":"2026-07-05T10:01:58.149671+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01771","citing_title":"LiveLight: Real-time Streaming Video Relighting with Interactive Control","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC","json":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC.json","graph_json":"https://pith.science/api/pith-number/BWL7QZRDBCMIYVVJIWEILVQMDC/graph.json","events_json":"https://pith.science/api/pith-number/BWL7QZRDBCMIYVVJIWEILVQMDC/events.json","paper":"https://pith.science/paper/BWL7QZRD"},"agent_actions":{"view_html":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC","download_json":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC.json","view_paper":"https://pith.science/paper/BWL7QZRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09756&json=true","fetch_graph":"https://pith.science/api/pith-number/BWL7QZRDBCMIYVVJIWEILVQMDC/graph.json","fetch_events":"https://pith.science/api/pith-number/BWL7QZRDBCMIYVVJIWEILVQMDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC/action/storage_attestation","attest_author":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC/action/author_attestation","sign_citation":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC/action/citation_signature","submit_replication":"https://pith.science/pith/BWL7QZRDBCMIYVVJIWEILVQMDC/action/replication_record"}},"created_at":"2026-07-05T10:01:58.149671+00:00","updated_at":"2026-07-05T10:01:58.149671+00:00"}