{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UPNJW3BEBGFXQSSI6WEVZCGKCG","short_pith_number":"pith:UPNJW3BE","schema_version":"1.0","canonical_sha256":"a3da9b6c24098b784a48f5895c88ca1188d1a7ff46ebbddf4b78ee550fc9ad28","source":{"kind":"arxiv","id":"2007.02442","version":4},"attestation_state":"computed","paper":{"title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Katja Schwarz, Michael Niemeyer, Yiyi Liao","submitted_at":"2020-07-05T20:37:39Z","abstract_excerpt":"While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, e.g., the object identity may vary with the viewpoint. In this paper, we propose"},"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":"2007.02442","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-05T20:37:39Z","cross_cats_sorted":[],"title_canon_sha256":"e5ce1a324c36545d5a87ddd0bff021aad2dea3d7d5426a27a0ea4b65c74f1137","abstract_canon_sha256":"f8eb92adcead4578b37d50c4dd678706b9796c0b8d307d7843e43df75a4617f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:22.152828Z","signature_b64":"ODSFD/u0uwgr7xe56eCiCFbdEpOJVUGhP8X05XY01GewCGBHuZHgz1cnUrdTKILNjOywl1f59j2+ffLlTMe4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3da9b6c24098b784a48f5895c88ca1188d1a7ff46ebbddf4b78ee550fc9ad28","last_reissued_at":"2026-07-05T02:27:22.152436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:22.152436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andreas Geiger, Katja Schwarz, Michael Niemeyer, Yiyi Liao","submitted_at":"2020-07-05T20:37:39Z","abstract_excerpt":"While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, e.g., the object identity may vary with the viewpoint. In this paper, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02442","kind":"arxiv","version":4},"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/2007.02442/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":"2007.02442","created_at":"2026-07-05T02:27:22.152493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.02442v4","created_at":"2026-07-05T02:27:22.152493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02442","created_at":"2026-07-05T02:27:22.152493+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPNJW3BEBGFX","created_at":"2026-07-05T02:27:22.152493+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPNJW3BEBGFXQSSI","created_at":"2026-07-05T02:27:22.152493+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPNJW3BE","created_at":"2026-07-05T02:27:22.152493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00754","citing_title":"CtrlNeRF: The Generative Neural Radiation Fields for the Controllable Synthesis of High-fidelity 3D-Aware Images","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG","json":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG.json","graph_json":"https://pith.science/api/pith-number/UPNJW3BEBGFXQSSI6WEVZCGKCG/graph.json","events_json":"https://pith.science/api/pith-number/UPNJW3BEBGFXQSSI6WEVZCGKCG/events.json","paper":"https://pith.science/paper/UPNJW3BE"},"agent_actions":{"view_html":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG","download_json":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG.json","view_paper":"https://pith.science/paper/UPNJW3BE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.02442&json=true","fetch_graph":"https://pith.science/api/pith-number/UPNJW3BEBGFXQSSI6WEVZCGKCG/graph.json","fetch_events":"https://pith.science/api/pith-number/UPNJW3BEBGFXQSSI6WEVZCGKCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG/action/storage_attestation","attest_author":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG/action/author_attestation","sign_citation":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG/action/citation_signature","submit_replication":"https://pith.science/pith/UPNJW3BEBGFXQSSI6WEVZCGKCG/action/replication_record"}},"created_at":"2026-07-05T02:27:22.152493+00:00","updated_at":"2026-07-05T02:27:22.152493+00:00"}