{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7H6RJDRRKSEF37RF6HDAFKACLE","short_pith_number":"pith:7H6RJDRR","schema_version":"1.0","canonical_sha256":"f9fd148e3154885dfe25f1c602a8025936c2d686e51943594dd549aa584f8200","source":{"kind":"arxiv","id":"2010.00114","version":1},"attestation_state":"computed","paper":{"title":"MaterialGAN: Reflectance Capture using a Generative SVBRDF Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cameron Smith, Kalyan Sunkavalli, Milo\\v{s} Ha\\v{s}an, Shuang Zhao, Yu Guo","submitted_at":"2020-09-30T21:33:00Z","abstract_excerpt":"We address the problem of reconstructing spatially-varying BRDFs from a small set of image measurements. This is a fundamentally under-constrained problem, and previous work has relied on using various regularization priors or on capturing many images to produce plausible results. In this work, we present MaterialGAN, a deep generative convolutional network based on StyleGAN2, trained to synthesize realistic SVBRDF parameter maps. We show that MaterialGAN can be used as a powerful material prior in an inverse rendering framework: we optimize in its latent representation to generate material ma"},"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":"2010.00114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-30T21:33:00Z","cross_cats_sorted":[],"title_canon_sha256":"cdd1c7bb6acaa595f017d6c7b8ff1b4ad35931e753e708296ee9ddddaa7ce77f","abstract_canon_sha256":"c070473e905050120991464d1c1728f87d259a7a5ce052fd94405ec265798fdb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:36.417304Z","signature_b64":"he++JtFoTJsGYRvXPlHJ44gHGB7KlXW3R67H6PhC2Gm/NpnXfv4PMqfGtUvr+PG1Vht6wiNdbbkRG1GiOQrcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9fd148e3154885dfe25f1c602a8025936c2d686e51943594dd549aa584f8200","last_reissued_at":"2026-07-05T01:57:36.416840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:36.416840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaterialGAN: Reflectance Capture using a Generative SVBRDF Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cameron Smith, Kalyan Sunkavalli, Milo\\v{s} Ha\\v{s}an, Shuang Zhao, Yu Guo","submitted_at":"2020-09-30T21:33:00Z","abstract_excerpt":"We address the problem of reconstructing spatially-varying BRDFs from a small set of image measurements. This is a fundamentally under-constrained problem, and previous work has relied on using various regularization priors or on capturing many images to produce plausible results. In this work, we present MaterialGAN, a deep generative convolutional network based on StyleGAN2, trained to synthesize realistic SVBRDF parameter maps. We show that MaterialGAN can be used as a powerful material prior in an inverse rendering framework: we optimize in its latent representation to generate material ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.00114","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/2010.00114/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":"2010.00114","created_at":"2026-07-05T01:57:36.416902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.00114v1","created_at":"2026-07-05T01:57:36.416902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.00114","created_at":"2026-07-05T01:57:36.416902+00:00"},{"alias_kind":"pith_short_12","alias_value":"7H6RJDRRKSEF","created_at":"2026-07-05T01:57:36.416902+00:00"},{"alias_kind":"pith_short_16","alias_value":"7H6RJDRRKSEF37RF","created_at":"2026-07-05T01:57:36.416902+00:00"},{"alias_kind":"pith_short_8","alias_value":"7H6RJDRR","created_at":"2026-07-05T01:57:36.416902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24081","citing_title":"Neural Enhancement of Analytical Appearance Models","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE","json":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE.json","graph_json":"https://pith.science/api/pith-number/7H6RJDRRKSEF37RF6HDAFKACLE/graph.json","events_json":"https://pith.science/api/pith-number/7H6RJDRRKSEF37RF6HDAFKACLE/events.json","paper":"https://pith.science/paper/7H6RJDRR"},"agent_actions":{"view_html":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE","download_json":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE.json","view_paper":"https://pith.science/paper/7H6RJDRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.00114&json=true","fetch_graph":"https://pith.science/api/pith-number/7H6RJDRRKSEF37RF6HDAFKACLE/graph.json","fetch_events":"https://pith.science/api/pith-number/7H6RJDRRKSEF37RF6HDAFKACLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE/action/storage_attestation","attest_author":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE/action/author_attestation","sign_citation":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE/action/citation_signature","submit_replication":"https://pith.science/pith/7H6RJDRRKSEF37RF6HDAFKACLE/action/replication_record"}},"created_at":"2026-07-05T01:57:36.416902+00:00","updated_at":"2026-07-05T01:57:36.416902+00:00"}