{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TZ7NN23UDHECMTZA6APOSEWOFA","short_pith_number":"pith:TZ7NN23U","schema_version":"1.0","canonical_sha256":"9e7ed6eb7419c8264f20f01ee912ce28014eadb1e6e5830c8f486759c83f67b1","source":{"kind":"arxiv","id":"2312.08568","version":2},"attestation_state":"computed","paper":{"title":"NViST: In the Wild New View Synthesis from a Single Image with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lourdes Agapito, Wonbong Jang","submitted_at":"2023-12-13T23:41:17Z","abstract_excerpt":"We propose NViST, a transformer-based model for efficient and generalizable novel-view synthesis from a single image for real-world scenes. In contrast to many methods that are trained on synthetic data, object-centred scenarios, or in a category-specific manner, NViST is trained on MVImgNet, a large-scale dataset of casually-captured real-world videos of hundreds of object categories with diverse backgrounds. NViST transforms image inputs directly into a radiance field, conditioned on camera parameters via adaptive layer normalisation. In practice, NViST exploits fine-tuned masked autoencoder"},"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":"2312.08568","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-13T23:41:17Z","cross_cats_sorted":[],"title_canon_sha256":"dab95e1c2e185887736cdf626f8d5868cf8f205aa6ff9e815e800b5e6ffa7120","abstract_canon_sha256":"6649dd5cad213b96a2d2f2198fa1cc8c977b9d9c57a17a389e8b0691711df1fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:49.317032Z","signature_b64":"ZUWcU6MypclH7+Kog+OkQg2jsgSSBjWXHaK3ts5BNySsDZ8fJ0t5s6JGw0eqksEVIxunk1Do5PZW5axg78z5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e7ed6eb7419c8264f20f01ee912ce28014eadb1e6e5830c8f486759c83f67b1","last_reissued_at":"2026-07-05T08:02:49.316533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:49.316533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NViST: In the Wild New View Synthesis from a Single Image with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lourdes Agapito, Wonbong Jang","submitted_at":"2023-12-13T23:41:17Z","abstract_excerpt":"We propose NViST, a transformer-based model for efficient and generalizable novel-view synthesis from a single image for real-world scenes. In contrast to many methods that are trained on synthetic data, object-centred scenarios, or in a category-specific manner, NViST is trained on MVImgNet, a large-scale dataset of casually-captured real-world videos of hundreds of object categories with diverse backgrounds. NViST transforms image inputs directly into a radiance field, conditioned on camera parameters via adaptive layer normalisation. In practice, NViST exploits fine-tuned masked autoencoder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08568","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/2312.08568/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":"2312.08568","created_at":"2026-07-05T08:02:49.316605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08568v2","created_at":"2026-07-05T08:02:49.316605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08568","created_at":"2026-07-05T08:02:49.316605+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZ7NN23UDHEC","created_at":"2026-07-05T08:02:49.316605+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZ7NN23UDHECMTZA","created_at":"2026-07-05T08:02:49.316605+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZ7NN23U","created_at":"2026-07-05T08:02:49.316605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11467","citing_title":"Exploiting Radiance Fields for Grasp Generation on Novel Synthetic Views","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA","json":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA.json","graph_json":"https://pith.science/api/pith-number/TZ7NN23UDHECMTZA6APOSEWOFA/graph.json","events_json":"https://pith.science/api/pith-number/TZ7NN23UDHECMTZA6APOSEWOFA/events.json","paper":"https://pith.science/paper/TZ7NN23U"},"agent_actions":{"view_html":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA","download_json":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA.json","view_paper":"https://pith.science/paper/TZ7NN23U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08568&json=true","fetch_graph":"https://pith.science/api/pith-number/TZ7NN23UDHECMTZA6APOSEWOFA/graph.json","fetch_events":"https://pith.science/api/pith-number/TZ7NN23UDHECMTZA6APOSEWOFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA/action/storage_attestation","attest_author":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA/action/author_attestation","sign_citation":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA/action/citation_signature","submit_replication":"https://pith.science/pith/TZ7NN23UDHECMTZA6APOSEWOFA/action/replication_record"}},"created_at":"2026-07-05T08:02:49.316605+00:00","updated_at":"2026-07-05T08:02:49.316605+00:00"}