{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:57ERPCCCXSEQ6KO4ULOLJI7FFG","short_pith_number":"pith:57ERPCCC","schema_version":"1.0","canonical_sha256":"efc9178842bc890f29dca2dcb4a3e5298c799912a27217bf060f8ab4d340984c","source":{"kind":"arxiv","id":"2303.01416","version":1},"attestation_state":"computed","paper":{"title":"3D generation on ImageNet","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Hsin-Ying Lee, Ivan Skorokhodov, Jian Ren, Peter Wonka, Sergey Tulyakov, Yinghao Xu","submitted_at":"2023-03-02T17:06:57Z","abstract_excerpt":"Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the scene. This makes them inapplicable to diverse, in-the-wild datasets of non-alignable scenes rendered from arbitrary camera poses. In this work, we develop a 3D generator with Generic Priors (3DGP): a 3D synthesis framework with more general assumptions about the training data, and show that it scales to very challenging datasets, like ImageNet. Our model is bas"},"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":"2303.01416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T17:06:57Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"4f28229d83e04c7dbf4ea57db138b6676a7f8bf63f2a12f1ecb0e3466ff99d52","abstract_canon_sha256":"f14d2365da7635ceb1f2409db28a27c60b144f2a5fe290666d684f27a1be122c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:30.615064Z","signature_b64":"VGqzrNcM8jJ4grKGuWogcyJWVUhN2ctBWolClTC3fyWt6sKtceKgv1A6ZETtnkFV9Arxldsf5IWXaIak3+W7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efc9178842bc890f29dca2dcb4a3e5298c799912a27217bf060f8ab4d340984c","last_reissued_at":"2026-07-05T05:47:30.614368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:30.614368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D generation on ImageNet","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Hsin-Ying Lee, Ivan Skorokhodov, Jian Ren, Peter Wonka, Sergey Tulyakov, Yinghao Xu","submitted_at":"2023-03-02T17:06:57Z","abstract_excerpt":"Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the scene. This makes them inapplicable to diverse, in-the-wild datasets of non-alignable scenes rendered from arbitrary camera poses. In this work, we develop a 3D generator with Generic Priors (3DGP): a 3D synthesis framework with more general assumptions about the training data, and show that it scales to very challenging datasets, like ImageNet. Our model is bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01416","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/2303.01416/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":"2303.01416","created_at":"2026-07-05T05:47:30.614491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01416v1","created_at":"2026-07-05T05:47:30.614491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01416","created_at":"2026-07-05T05:47:30.614491+00:00"},{"alias_kind":"pith_short_12","alias_value":"57ERPCCCXSEQ","created_at":"2026-07-05T05:47:30.614491+00:00"},{"alias_kind":"pith_short_16","alias_value":"57ERPCCCXSEQ6KO4","created_at":"2026-07-05T05:47:30.614491+00:00"},{"alias_kind":"pith_short_8","alias_value":"57ERPCCC","created_at":"2026-07-05T05:47:30.614491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04035","citing_title":"Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2412.01506","citing_title":"Structured 3D Latents for Scalable and Versatile 3D Generation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03453","citing_title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04035","citing_title":"Large-Scale High-Quality 3D Gaussian Head Reconstruction from Multi-View Captures","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG","json":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG.json","graph_json":"https://pith.science/api/pith-number/57ERPCCCXSEQ6KO4ULOLJI7FFG/graph.json","events_json":"https://pith.science/api/pith-number/57ERPCCCXSEQ6KO4ULOLJI7FFG/events.json","paper":"https://pith.science/paper/57ERPCCC"},"agent_actions":{"view_html":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG","download_json":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG.json","view_paper":"https://pith.science/paper/57ERPCCC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01416&json=true","fetch_graph":"https://pith.science/api/pith-number/57ERPCCCXSEQ6KO4ULOLJI7FFG/graph.json","fetch_events":"https://pith.science/api/pith-number/57ERPCCCXSEQ6KO4ULOLJI7FFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG/action/storage_attestation","attest_author":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG/action/author_attestation","sign_citation":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG/action/citation_signature","submit_replication":"https://pith.science/pith/57ERPCCCXSEQ6KO4ULOLJI7FFG/action/replication_record"}},"created_at":"2026-07-05T05:47:30.614491+00:00","updated_at":"2026-07-05T05:47:30.614491+00:00"}