{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6YPUYCVJ4TNKZNPMVQZVLDEJ5R","short_pith_number":"pith:6YPUYCVJ","schema_version":"1.0","canonical_sha256":"f61f4c0aa9e4daacb5ecac33558c89ec550c1832ddb05d9b6610f471c5b46e4c","source":{"kind":"arxiv","id":"2506.19844","version":1},"attestation_state":"computed","paper":{"title":"Active View Selector: Fast and Accurate Active View Selection with Cross Reference Image Quality Assessment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruining Li, Victor Adrian Prisacariu, Yash Bhalgat, Zirui Wang","submitted_at":"2025-06-24T17:59:15Z","abstract_excerpt":"We tackle active view selection in novel view synthesis and 3D reconstruction. Existing methods like FisheRF and ActiveNeRF select the next best view by minimizing uncertainty or maximizing information gain in 3D, but they require specialized designs for different 3D representations and involve complex modelling in 3D space. Instead, we reframe this as a 2D image quality assessment (IQA) task, selecting views where current renderings have the lowest quality. Since ground-truth images for candidate views are unavailable, full-reference metrics like PSNR and SSIM are inapplicable, while no-refer"},"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":"2506.19844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T17:59:15Z","cross_cats_sorted":[],"title_canon_sha256":"bcd712a7b7022ceaadc1598edfa6c271deb66938ba6073d14616893968092c0a","abstract_canon_sha256":"0f663390193ad41e3c3646beb601314f901d732cd2686b6d7f35eda4bbd0c7be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:39.424668Z","signature_b64":"a+oD/q5M6KYFotsr3ybRBc3tBPuKIK7HPrMelXxqeLEM11+hyXWrEQJwxVava6D83uxA3oVh+78uwikeLD0NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f61f4c0aa9e4daacb5ecac33558c89ec550c1832ddb05d9b6610f471c5b46e4c","last_reissued_at":"2026-07-05T11:26:39.424195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:39.424195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active View Selector: Fast and Accurate Active View Selection with Cross Reference Image Quality Assessment","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruining Li, Victor Adrian Prisacariu, Yash Bhalgat, Zirui Wang","submitted_at":"2025-06-24T17:59:15Z","abstract_excerpt":"We tackle active view selection in novel view synthesis and 3D reconstruction. Existing methods like FisheRF and ActiveNeRF select the next best view by minimizing uncertainty or maximizing information gain in 3D, but they require specialized designs for different 3D representations and involve complex modelling in 3D space. Instead, we reframe this as a 2D image quality assessment (IQA) task, selecting views where current renderings have the lowest quality. Since ground-truth images for candidate views are unavailable, full-reference metrics like PSNR and SSIM are inapplicable, while no-refer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19844","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/2506.19844/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":"2506.19844","created_at":"2026-07-05T11:26:39.424249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19844v1","created_at":"2026-07-05T11:26:39.424249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19844","created_at":"2026-07-05T11:26:39.424249+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YPUYCVJ4TNK","created_at":"2026-07-05T11:26:39.424249+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YPUYCVJ4TNKZNPM","created_at":"2026-07-05T11:26:39.424249+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YPUYCVJ","created_at":"2026-07-05T11:26:39.424249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.15355","citing_title":"DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04576","citing_title":"PR-IQA: Partial-Reference Image Quality Assessment for Diffusion-Based Novel View Synthesis","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R","json":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R.json","graph_json":"https://pith.science/api/pith-number/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/graph.json","events_json":"https://pith.science/api/pith-number/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/events.json","paper":"https://pith.science/paper/6YPUYCVJ"},"agent_actions":{"view_html":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R","download_json":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R.json","view_paper":"https://pith.science/paper/6YPUYCVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19844&json=true","fetch_graph":"https://pith.science/api/pith-number/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/graph.json","fetch_events":"https://pith.science/api/pith-number/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/action/storage_attestation","attest_author":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/action/author_attestation","sign_citation":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/action/citation_signature","submit_replication":"https://pith.science/pith/6YPUYCVJ4TNKZNPMVQZVLDEJ5R/action/replication_record"}},"created_at":"2026-07-05T11:26:39.424249+00:00","updated_at":"2026-07-05T11:26:39.424249+00:00"}