{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IYEV7F7AFXMN5YW3NUGWHBB5LT","short_pith_number":"pith:IYEV7F7A","schema_version":"1.0","canonical_sha256":"46095f97e02dd8dee2db6d0d63843d5cff7c9a6e0ed61159549b7f49660395e6","source":{"kind":"arxiv","id":"2104.07652","version":2},"attestation_state":"computed","paper":{"title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Patrick Esser, Robin Rombach","submitted_at":"2021-04-15T17:58:05Z","abstract_excerpt":"Is a geometric model required to synthesize novel views from a single image? Being bound to local convolutions, CNNs need explicit 3D biases to model geometric transformations. In contrast, we demonstrate that a transformer-based model can synthesize entirely novel views without any hand-engineered 3D biases. This is achieved by (i) a global attention mechanism for implicitly learning long-range 3D correspondences between source and target views, and (ii) a probabilistic formulation necessary to capture the ambiguity inherent in predicting novel views from a single image, thereby overcoming th"},"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":"2104.07652","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-15T17:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"225b8a920afd695e00647af6a1d75830e4987efb8fccf84353ab880737a9b0f8","abstract_canon_sha256":"fcfbe54bb8ae5e7b0f53fffa94b27e7f522f86ca425303db1e1c0e2953b5f6aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:45.542135Z","signature_b64":"cg+xvdtAiKPSJ6dm0uT2OGFqJx+Bp44fHCCuBdBn0VHGx+Jx9S3Ryup9lcsBKMtk4JQguKKx8NJqH+7PNzBvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46095f97e02dd8dee2db6d0d63843d5cff7c9a6e0ed61159549b7f49660395e6","last_reissued_at":"2026-07-05T03:09:45.541694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:45.541694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Patrick Esser, Robin Rombach","submitted_at":"2021-04-15T17:58:05Z","abstract_excerpt":"Is a geometric model required to synthesize novel views from a single image? Being bound to local convolutions, CNNs need explicit 3D biases to model geometric transformations. In contrast, we demonstrate that a transformer-based model can synthesize entirely novel views without any hand-engineered 3D biases. This is achieved by (i) a global attention mechanism for implicitly learning long-range 3D correspondences between source and target views, and (ii) a probabilistic formulation necessary to capture the ambiguity inherent in predicting novel views from a single image, thereby overcoming th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07652","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/2104.07652/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":"2104.07652","created_at":"2026-07-05T03:09:45.541753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.07652v2","created_at":"2026-07-05T03:09:45.541753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07652","created_at":"2026-07-05T03:09:45.541753+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYEV7F7AFXMN","created_at":"2026-07-05T03:09:45.541753+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYEV7F7AFXMN5YW3","created_at":"2026-07-05T03:09:45.541753+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYEV7F7A","created_at":"2026-07-05T03:09:45.541753+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14464","citing_title":"LiftRefine: Progressively Refined View Synthesis from 3D Lifting with Volume-Triplane Representations","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT","json":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT.json","graph_json":"https://pith.science/api/pith-number/IYEV7F7AFXMN5YW3NUGWHBB5LT/graph.json","events_json":"https://pith.science/api/pith-number/IYEV7F7AFXMN5YW3NUGWHBB5LT/events.json","paper":"https://pith.science/paper/IYEV7F7A"},"agent_actions":{"view_html":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT","download_json":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT.json","view_paper":"https://pith.science/paper/IYEV7F7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.07652&json=true","fetch_graph":"https://pith.science/api/pith-number/IYEV7F7AFXMN5YW3NUGWHBB5LT/graph.json","fetch_events":"https://pith.science/api/pith-number/IYEV7F7AFXMN5YW3NUGWHBB5LT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT/action/storage_attestation","attest_author":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT/action/author_attestation","sign_citation":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT/action/citation_signature","submit_replication":"https://pith.science/pith/IYEV7F7AFXMN5YW3NUGWHBB5LT/action/replication_record"}},"created_at":"2026-07-05T03:09:45.541753+00:00","updated_at":"2026-07-05T03:09:45.541753+00:00"}