{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IAFZ2R4E4GMHPDCTF3KMOYVF3X","short_pith_number":"pith:IAFZ2R4E","schema_version":"1.0","canonical_sha256":"400b9d4784e198778c532ed4c762a5ddf85e9c44f1c0b0a46b2b90bdddd58b24","source":{"kind":"arxiv","id":"2603.23297","version":2},"attestation_state":"computed","paper":{"title":"Drop-In Perceptual Optimization for 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Ezgi Ozyilkan, Jona Ball\\'e, Kedar Tatwawadi, Oren Rippel, Zhiqi Chen","submitted_at":"2026-03-23T17:42:49Z","abstract_excerpt":"Despite their output being ultimately consumed by human viewers, 3D Gaussian Splatting (3DGS) methods often rely on ad-hoc combinations of pixel-level losses, resulting in blurry renderings. To address this, we systematically explore perceptual optimization strategies for 3DGS by searching over a diverse set of distortion losses. We conduct the first-of-its-kind large-scale human subjective study on 3DGS, involving 39,320 pairwise ratings across several datasets and 3DGS frameworks. A regularized version of Wasserstein Distortion, which we call WD-R, emerges as the clear winner, excelling at r"},"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":"2603.23297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-23T17:42:49Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"ead89a605391bd84f12692c936e94a56ecabb7b357b805989eec36ed47fb6b26","abstract_canon_sha256":"b969e3704dc5470667ad10a2adda783fdca3f50925247b7b6ce64f813179eb25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:24.519732Z","signature_b64":"+Uz3oZa5xjHE/KCITuTkWDJKsGrlnqC+uSbFfPdnowPTsfFUcpov/IigyaAbTOLM0/Ylvn5gg27u9WEcj+8lBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"400b9d4784e198778c532ed4c762a5ddf85e9c44f1c0b0a46b2b90bdddd58b24","last_reissued_at":"2026-07-01T01:18:24.519209Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:24.519209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drop-In Perceptual Optimization for 3D Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Ezgi Ozyilkan, Jona Ball\\'e, Kedar Tatwawadi, Oren Rippel, Zhiqi Chen","submitted_at":"2026-03-23T17:42:49Z","abstract_excerpt":"Despite their output being ultimately consumed by human viewers, 3D Gaussian Splatting (3DGS) methods often rely on ad-hoc combinations of pixel-level losses, resulting in blurry renderings. To address this, we systematically explore perceptual optimization strategies for 3DGS by searching over a diverse set of distortion losses. We conduct the first-of-its-kind large-scale human subjective study on 3DGS, involving 39,320 pairwise ratings across several datasets and 3DGS frameworks. A regularized version of Wasserstein Distortion, which we call WD-R, emerges as the clear winner, excelling at r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.23297","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/2603.23297/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":"2603.23297","created_at":"2026-07-01T01:18:24.519274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.23297v2","created_at":"2026-07-01T01:18:24.519274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23297","created_at":"2026-07-01T01:18:24.519274+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAFZ2R4E4GMH","created_at":"2026-07-01T01:18:24.519274+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAFZ2R4E4GMHPDCT","created_at":"2026-07-01T01:18:24.519274+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAFZ2R4E","created_at":"2026-07-01T01:18:24.519274+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.05155","citing_title":"Aes3D: Aesthetic Assessment in 3D Gaussian Splatting","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05155","citing_title":"Aes3D: Aesthetic Assessment in 3D Gaussian Splatting","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X","json":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X.json","graph_json":"https://pith.science/api/pith-number/IAFZ2R4E4GMHPDCTF3KMOYVF3X/graph.json","events_json":"https://pith.science/api/pith-number/IAFZ2R4E4GMHPDCTF3KMOYVF3X/events.json","paper":"https://pith.science/paper/IAFZ2R4E"},"agent_actions":{"view_html":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X","download_json":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X.json","view_paper":"https://pith.science/paper/IAFZ2R4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.23297&json=true","fetch_graph":"https://pith.science/api/pith-number/IAFZ2R4E4GMHPDCTF3KMOYVF3X/graph.json","fetch_events":"https://pith.science/api/pith-number/IAFZ2R4E4GMHPDCTF3KMOYVF3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X/action/storage_attestation","attest_author":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X/action/author_attestation","sign_citation":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X/action/citation_signature","submit_replication":"https://pith.science/pith/IAFZ2R4E4GMHPDCTF3KMOYVF3X/action/replication_record"}},"created_at":"2026-07-01T01:18:24.519274+00:00","updated_at":"2026-07-01T01:18:24.519274+00:00"}