{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G3KSBUBFYOIJ5VI4UTRC3XTZQU","short_pith_number":"pith:G3KSBUBF","schema_version":"1.0","canonical_sha256":"36d520d025c3909ed51ca4e22dde7985272e41befe403197493368ad0ae13931","source":{"kind":"arxiv","id":"1910.00287","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Generative 3D Shape Learning from Natural Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Attila Szab\\'o, Givi Meishvili, Paolo Favaro","submitted_at":"2019-10-01T10:20:59Z","abstract_excerpt":"In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo video, and ego-motion during the training. Our approach follows the general strategy of Generative Adversarial Networks, where an image generator network learns to create image samples that are realistic enough to fool a discriminator network into believing that they are natural images. In contrast, in our approach the image generation is split into 2 stages. In"},"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":"1910.00287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-01T10:20:59Z","cross_cats_sorted":[],"title_canon_sha256":"63f92e7011d1ce711f3651aa2d95155dd626cfba510f0b3c22b1ab55da4300ed","abstract_canon_sha256":"58b97e3baa6a4a1bccaa98321dad532fa194d9cfe48ceed69e5a8b9846665f3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:44.301508Z","signature_b64":"xoHnLKYGZzKAamdt+6t9sNsn7QV5eSUYO7YOl1oZomAR7RTDocFzpjjdfVj0SgGOb0tMywk10Tmo5EEATe94Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36d520d025c3909ed51ca4e22dde7985272e41befe403197493368ad0ae13931","last_reissued_at":"2026-07-05T00:08:44.301120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:44.301120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Generative 3D Shape Learning from Natural Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Attila Szab\\'o, Givi Meishvili, Paolo Favaro","submitted_at":"2019-10-01T10:20:59Z","abstract_excerpt":"In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo video, and ego-motion during the training. Our approach follows the general strategy of Generative Adversarial Networks, where an image generator network learns to create image samples that are realistic enough to fool a discriminator network into believing that they are natural images. In contrast, in our approach the image generation is split into 2 stages. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.00287","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/1910.00287/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":"1910.00287","created_at":"2026-07-05T00:08:44.301178+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.00287v1","created_at":"2026-07-05T00:08:44.301178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.00287","created_at":"2026-07-05T00:08:44.301178+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3KSBUBFYOIJ","created_at":"2026-07-05T00:08:44.301178+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3KSBUBFYOIJ5VI4","created_at":"2026-07-05T00:08:44.301178+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3KSBUBF","created_at":"2026-07-05T00:08:44.301178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27659","citing_title":"GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01450","citing_title":"Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU","json":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU.json","graph_json":"https://pith.science/api/pith-number/G3KSBUBFYOIJ5VI4UTRC3XTZQU/graph.json","events_json":"https://pith.science/api/pith-number/G3KSBUBFYOIJ5VI4UTRC3XTZQU/events.json","paper":"https://pith.science/paper/G3KSBUBF"},"agent_actions":{"view_html":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU","download_json":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU.json","view_paper":"https://pith.science/paper/G3KSBUBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.00287&json=true","fetch_graph":"https://pith.science/api/pith-number/G3KSBUBFYOIJ5VI4UTRC3XTZQU/graph.json","fetch_events":"https://pith.science/api/pith-number/G3KSBUBFYOIJ5VI4UTRC3XTZQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU/action/storage_attestation","attest_author":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU/action/author_attestation","sign_citation":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU/action/citation_signature","submit_replication":"https://pith.science/pith/G3KSBUBFYOIJ5VI4UTRC3XTZQU/action/replication_record"}},"created_at":"2026-07-05T00:08:44.301178+00:00","updated_at":"2026-07-05T00:08:44.301178+00:00"}