{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YBT5XWMZEFDY5TC6IJOUYKRUZK","short_pith_number":"pith:YBT5XWMZ","schema_version":"1.0","canonical_sha256":"c067dbd99921478ecc5e425d4c2a34cabd16c031acbab7ce9608ea2e35f16574","source":{"kind":"arxiv","id":"2305.02981","version":2},"attestation_state":"computed","paper":{"title":"Adversarially-Guided Portrait Matting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Karen Efremyan, Sergej Chicherin","submitted_at":"2023-05-04T16:45:04Z","abstract_excerpt":"We present a method for generating alpha mattes using a limited data source. We pretrain a novel transformerbased model (StyleMatte) on portrait datasets. We utilize this model to provide image-mask pairs for the StyleGAN3-based network (StyleMatteGAN). This network is trained unsupervisedly and generates previously unseen imagemask training pairs that are fed back to StyleMatte. We demonstrate that the performance of the matte pulling network improves during this cycle and obtains top results on the human portraits and state-of-the-art metrics on animals dataset. Furthermore, StyleMatteGAN pr"},"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":"2305.02981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T16:45:04Z","cross_cats_sorted":[],"title_canon_sha256":"9395ec58590065bf29f69213757257fd984da17e6178243fb0672f8d8c47148f","abstract_canon_sha256":"7411a62ce7eb6a467a4b4e6f7f6b1f473698d093c3646cbe334546fcc49962f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:48.894647Z","signature_b64":"X9mbaSAJLrlKyaWaLdsSR77ehBOCEOJHe6plwUQO4jHRphIf/q/gXBFGka8QRHjMdFsOYVCudyPEXDJEKObXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c067dbd99921478ecc5e425d4c2a34cabd16c031acbab7ce9608ea2e35f16574","last_reissued_at":"2026-07-05T06:12:48.894163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:48.894163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarially-Guided Portrait Matting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Karen Efremyan, Sergej Chicherin","submitted_at":"2023-05-04T16:45:04Z","abstract_excerpt":"We present a method for generating alpha mattes using a limited data source. We pretrain a novel transformerbased model (StyleMatte) on portrait datasets. We utilize this model to provide image-mask pairs for the StyleGAN3-based network (StyleMatteGAN). This network is trained unsupervisedly and generates previously unseen imagemask training pairs that are fed back to StyleMatte. We demonstrate that the performance of the matte pulling network improves during this cycle and obtains top results on the human portraits and state-of-the-art metrics on animals dataset. Furthermore, StyleMatteGAN pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02981","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/2305.02981/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":"2305.02981","created_at":"2026-07-05T06:12:48.894225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02981v2","created_at":"2026-07-05T06:12:48.894225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02981","created_at":"2026-07-05T06:12:48.894225+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBT5XWMZEFDY","created_at":"2026-07-05T06:12:48.894225+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBT5XWMZEFDY5TC6","created_at":"2026-07-05T06:12:48.894225+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBT5XWMZ","created_at":"2026-07-05T06:12:48.894225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03351","citing_title":"GUAVA: Generalizable Upper Body 3D Gaussian Avatar","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK","json":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK.json","graph_json":"https://pith.science/api/pith-number/YBT5XWMZEFDY5TC6IJOUYKRUZK/graph.json","events_json":"https://pith.science/api/pith-number/YBT5XWMZEFDY5TC6IJOUYKRUZK/events.json","paper":"https://pith.science/paper/YBT5XWMZ"},"agent_actions":{"view_html":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK","download_json":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK.json","view_paper":"https://pith.science/paper/YBT5XWMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02981&json=true","fetch_graph":"https://pith.science/api/pith-number/YBT5XWMZEFDY5TC6IJOUYKRUZK/graph.json","fetch_events":"https://pith.science/api/pith-number/YBT5XWMZEFDY5TC6IJOUYKRUZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK/action/storage_attestation","attest_author":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK/action/author_attestation","sign_citation":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK/action/citation_signature","submit_replication":"https://pith.science/pith/YBT5XWMZEFDY5TC6IJOUYKRUZK/action/replication_record"}},"created_at":"2026-07-05T06:12:48.894225+00:00","updated_at":"2026-07-05T06:12:48.894225+00:00"}