{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RRPDVVCIYSFFWGB3MGKYDTQGAO","short_pith_number":"pith:RRPDVVCI","schema_version":"1.0","canonical_sha256":"8c5e3ad448c48a5b183b619581ce06038dc70b823b24eeffd61b96c0e56c1b73","source":{"kind":"arxiv","id":"1904.02672","version":1},"attestation_state":"computed","paper":{"title":"Deep Multi-class Adversarial Specularity Removal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Bartoli, John Lin, Mohamed El Amine Seddik, Mohamed Tamaazousti, Youssef Tamaazousti","submitted_at":"2019-04-04T17:14:14Z","abstract_excerpt":"We propose a novel learning approach, in the form of a fully-convolutional neural network (CNN), which automatically and consistently removes specular highlights from a single image by generating its diffuse component. To train the generative network, we define an adversarial loss on a discriminative network as in the GAN framework and combined it with a content loss. In contrast to existing GAN approaches, we implemented the discriminator to be a multi-class classifier instead of a binary one, to find more constraining features. This helps the network pinpoint the diffuse manifold by providin"},"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":"1904.02672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-04T17:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"dafae46e2cecdf7db98ea1726d5865034dafc61f38120795fdd00deb0c361e1b","abstract_canon_sha256":"0c09d12ce976536c4dae6c35b6047692cf88280252c570558554da9525401699"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:23.053740Z","signature_b64":"nW34gXEJpUy2Fo4zfxq8s1HLK0Z6hEnwOglqRcBux4quRCUSv11TDxk2j5DWwa3G1Bmb+ME9yJqGq5xNr2m/AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c5e3ad448c48a5b183b619581ce06038dc70b823b24eeffd61b96c0e56c1b73","last_reissued_at":"2026-05-17T23:49:23.053254Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:23.053254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Multi-class Adversarial Specularity Removal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Bartoli, John Lin, Mohamed El Amine Seddik, Mohamed Tamaazousti, Youssef Tamaazousti","submitted_at":"2019-04-04T17:14:14Z","abstract_excerpt":"We propose a novel learning approach, in the form of a fully-convolutional neural network (CNN), which automatically and consistently removes specular highlights from a single image by generating its diffuse component. To train the generative network, we define an adversarial loss on a discriminative network as in the GAN framework and combined it with a content loss. In contrast to existing GAN approaches, we implemented the discriminator to be a multi-class classifier instead of a binary one, to find more constraining features. This helps the network pinpoint the diffuse manifold by providin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02672","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":""},"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":"1904.02672","created_at":"2026-05-17T23:49:23.053327+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02672v1","created_at":"2026-05-17T23:49:23.053327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02672","created_at":"2026-05-17T23:49:23.053327+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRPDVVCIYSFF","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRPDVVCIYSFFWGB3","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRPDVVCI","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO","json":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO.json","graph_json":"https://pith.science/api/pith-number/RRPDVVCIYSFFWGB3MGKYDTQGAO/graph.json","events_json":"https://pith.science/api/pith-number/RRPDVVCIYSFFWGB3MGKYDTQGAO/events.json","paper":"https://pith.science/paper/RRPDVVCI"},"agent_actions":{"view_html":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO","download_json":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO.json","view_paper":"https://pith.science/paper/RRPDVVCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02672&json=true","fetch_graph":"https://pith.science/api/pith-number/RRPDVVCIYSFFWGB3MGKYDTQGAO/graph.json","fetch_events":"https://pith.science/api/pith-number/RRPDVVCIYSFFWGB3MGKYDTQGAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO/action/storage_attestation","attest_author":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO/action/author_attestation","sign_citation":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO/action/citation_signature","submit_replication":"https://pith.science/pith/RRPDVVCIYSFFWGB3MGKYDTQGAO/action/replication_record"}},"created_at":"2026-05-17T23:49:23.053327+00:00","updated_at":"2026-05-17T23:49:23.053327+00:00"}