{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6FB6CFZSXFREXYDF6DVGV5WFZA","short_pith_number":"pith:6FB6CFZS","schema_version":"1.0","canonical_sha256":"f143e11732b9624be065f0ea6af6c5c829cf4ea3dd63fe7b352f85fd6f910576","source":{"kind":"arxiv","id":"2303.12326","version":1},"attestation_state":"computed","paper":{"title":"Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Hongyu Liu, Yiming Zhu, Yu Li, Ziyang Yuan","submitted_at":"2023-03-22T05:51:53Z","abstract_excerpt":"3D GAN inversion aims to achieve high reconstruction fidelity and reasonable 3D geometry simultaneously from a single image input. However, existing 3D GAN inversion methods rely on time-consuming optimization for each individual case. In this work, we introduce a novel encoder-based inversion framework based on EG3D, one of the most widely-used 3D GAN models. We leverage the inherent properties of EG3D's latent space to design a discriminator and a background depth regularization. This enables us to train a geometry-aware encoder capable of converting the input image into corresponding latent"},"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":"2303.12326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T05:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"b93d8fb7999288ef66626ee93727164944b5ccfa7581ef35d7b6cd130342cc1c","abstract_canon_sha256":"cf2c285c8613d24b39ed409afe81004a32d5e08d77939f04e2b40c6911add6da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:39.920435Z","signature_b64":"LP4cuxI2+HllW7y7RC+7Hy2zJL48M2URvJdJGw4czMIldxZaxetDKpkfEQuBqop7h6KD/b1zykvxHySbwiZ/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f143e11732b9624be065f0ea6af6c5c829cf4ea3dd63fe7b352f85fd6f910576","last_reissued_at":"2026-07-05T05:53:39.919990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:39.919990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Hongyu Liu, Yiming Zhu, Yu Li, Ziyang Yuan","submitted_at":"2023-03-22T05:51:53Z","abstract_excerpt":"3D GAN inversion aims to achieve high reconstruction fidelity and reasonable 3D geometry simultaneously from a single image input. However, existing 3D GAN inversion methods rely on time-consuming optimization for each individual case. In this work, we introduce a novel encoder-based inversion framework based on EG3D, one of the most widely-used 3D GAN models. We leverage the inherent properties of EG3D's latent space to design a discriminator and a background depth regularization. This enables us to train a geometry-aware encoder capable of converting the input image into corresponding latent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12326","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/2303.12326/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":"2303.12326","created_at":"2026-07-05T05:53:39.920048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12326v1","created_at":"2026-07-05T05:53:39.920048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12326","created_at":"2026-07-05T05:53:39.920048+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FB6CFZSXFRE","created_at":"2026-07-05T05:53:39.920048+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FB6CFZSXFREXYDF","created_at":"2026-07-05T05:53:39.920048+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FB6CFZS","created_at":"2026-07-05T05:53:39.920048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18156","citing_title":"ReAge3D: Re-Aging 3D Faces with View Consistency","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA","json":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA.json","graph_json":"https://pith.science/api/pith-number/6FB6CFZSXFREXYDF6DVGV5WFZA/graph.json","events_json":"https://pith.science/api/pith-number/6FB6CFZSXFREXYDF6DVGV5WFZA/events.json","paper":"https://pith.science/paper/6FB6CFZS"},"agent_actions":{"view_html":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA","download_json":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA.json","view_paper":"https://pith.science/paper/6FB6CFZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12326&json=true","fetch_graph":"https://pith.science/api/pith-number/6FB6CFZSXFREXYDF6DVGV5WFZA/graph.json","fetch_events":"https://pith.science/api/pith-number/6FB6CFZSXFREXYDF6DVGV5WFZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA/action/storage_attestation","attest_author":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA/action/author_attestation","sign_citation":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA/action/citation_signature","submit_replication":"https://pith.science/pith/6FB6CFZSXFREXYDF6DVGV5WFZA/action/replication_record"}},"created_at":"2026-07-05T05:53:39.920048+00:00","updated_at":"2026-07-05T05:53:39.920048+00:00"}