{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CN3MTWMIG4TKFS2ESCMPO62AH2","short_pith_number":"pith:CN3MTWMI","schema_version":"1.0","canonical_sha256":"1376c9d9883726a2cb449098f77b403ebbbeed9d86ed4b3d0f49e6e6f793d90e","source":{"kind":"arxiv","id":"2605.05155","version":2},"attestation_state":"computed","paper":{"title":"Aes3D: Aesthetic Assessment in 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"A lightweight model predicts aesthetic scores for 3D scenes directly from Gaussian splat primitives without rendering images.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boyu Wei, Chuanzhi Xu, Haodong Chen, Haoxian Zhou, Qiang Qu, Weidong Cai, Xuanhua Yin, Zihan Deng","submitted_at":"2026-05-06T17:27:09Z","abstract_excerpt":"As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes such as composition, harmony, and visual appeal. This limitation comes from two key challenges: (1) the absence of general 3DGS datasets with aesthetic annotations, and (2) the intrinsic nature of 3DGS as a low-"},"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":"2605.05155","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-06T17:27:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ab3ff04493f28cdf90b4f2ff3b00929fadd08d185c34c300eb3509c6af3fc479","abstract_canon_sha256":"3cfb8664d8d4e1e9c720866d64879f4ed132b6c9a4e97401ccce46540de4c38f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:32.296233Z","signature_b64":"KRfTbH/myWEeuNXonxqxw8mCoLS+EGQlyYf8aNupryyKkSjl0MYysYWLqkJFUSDb+Q7MfNkLP13BqC0QGDwDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1376c9d9883726a2cb449098f77b403ebbbeed9d86ed4b3d0f49e6e6f793d90e","last_reissued_at":"2026-05-26T01:03:32.295434Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:32.295434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aes3D: Aesthetic Assessment in 3D Gaussian Splatting","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"A lightweight model predicts aesthetic scores for 3D scenes directly from Gaussian splat primitives without rendering images.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Boyu Wei, Chuanzhi Xu, Haodong Chen, Haoxian Zhou, Qiang Qu, Weidong Cai, Xuanhua Yin, Zihan Deng","submitted_at":"2026-05-06T17:27:09Z","abstract_excerpt":"As 3D Gaussian Splatting (3DGS) gains attention in immersive media and digital content creation, assessing the aesthetics of 3D scenes becomes important in helping creators build more visually compelling 3D content. However, existing evaluation methods for 3D scenes primarily emphasize reconstruction fidelity and perceptual realism, largely overlooking higher-level aesthetic attributes such as composition, harmony, and visual appeal. This limitation comes from two key challenges: (1) the absence of general 3DGS datasets with aesthetic annotations, and (2) the intrinsic nature of 3DGS as a low-"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we propose Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes. Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment... In addition, we present Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations... Experimental results demonstrate that our approach achieves strong performance while maintaining a lightweight design, establishing a new benchmark for 3D scene aesthetic assessment.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That high-level aesthetic attributes such as composition, harmony, and visual appeal can be captured and accurately regressed from low-level 3D Gaussian primitives alone, without rendering multi-view images, using a lightweight network trained via aesthetics-supervised learning on multi-view 3DGS representations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Aes3D creates the first dedicated dataset for 3D scene aesthetics and a model that predicts aesthetic scores straight from 3D Gaussian primitives.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A lightweight model predicts aesthetic scores for 3D scenes directly from Gaussian splat primitives without rendering images.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2194fb02e288ddd524c6d7a42aae21c978a08a2928bb60b9187d6dfc34e9251b"},"source":{"id":"2605.05155","kind":"arxiv","version":2},"verdict":{"id":"a04ea84c-e1c7-4c1a-bbcd-096c4d616be4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T16:49:07.194983Z","strongest_claim":"we propose Aes3D, the first systematic framework for assessing the aesthetics of 3D neural rendering scenes. Aes3D includes Aesthetic3D, the first dataset dedicated to 3D scene aesthetic assessment... In addition, we present Aes3DGSNet, a lightweight model that directly predicts scene-level aesthetic scores from 3DGS representations... Experimental results demonstrate that our approach achieves strong performance while maintaining a lightweight design, establishing a new benchmark for 3D scene aesthetic assessment.","one_line_summary":"Aes3D creates the first dedicated dataset for 3D scene aesthetics and a model that predicts aesthetic scores straight from 3D Gaussian primitives.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That high-level aesthetic attributes such as composition, harmony, and visual appeal can be captured and accurately regressed from low-level 3D Gaussian primitives alone, without rendering multi-view images, using a lightweight network trained via aesthetics-supervised learning on multi-view 3DGS representations.","pith_extraction_headline":"A lightweight model predicts aesthetic scores for 3D scenes directly from Gaussian splat primitives without rendering images."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.05155/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T10:36:02.944451Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T21:01:19.815713Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T13:48:20.118775Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2b650912287c675c8495b5c975b98e342f7a1178a92721f5b7989daa92f77972"},"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":"2605.05155","created_at":"2026-05-26T01:03:32.295555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.05155v2","created_at":"2026-05-26T01:03:32.295555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.05155","created_at":"2026-05-26T01:03:32.295555+00:00"},{"alias_kind":"pith_short_12","alias_value":"CN3MTWMIG4TK","created_at":"2026-05-26T01:03:32.295555+00:00"},{"alias_kind":"pith_short_16","alias_value":"CN3MTWMIG4TKFS2E","created_at":"2026-05-26T01:03:32.295555+00:00"},{"alias_kind":"pith_short_8","alias_value":"CN3MTWMI","created_at":"2026-05-26T01:03:32.295555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2","json":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2.json","graph_json":"https://pith.science/api/pith-number/CN3MTWMIG4TKFS2ESCMPO62AH2/graph.json","events_json":"https://pith.science/api/pith-number/CN3MTWMIG4TKFS2ESCMPO62AH2/events.json","paper":"https://pith.science/paper/CN3MTWMI"},"agent_actions":{"view_html":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2","download_json":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2.json","view_paper":"https://pith.science/paper/CN3MTWMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.05155&json=true","fetch_graph":"https://pith.science/api/pith-number/CN3MTWMIG4TKFS2ESCMPO62AH2/graph.json","fetch_events":"https://pith.science/api/pith-number/CN3MTWMIG4TKFS2ESCMPO62AH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2/action/storage_attestation","attest_author":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2/action/author_attestation","sign_citation":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2/action/citation_signature","submit_replication":"https://pith.science/pith/CN3MTWMIG4TKFS2ESCMPO62AH2/action/replication_record"}},"created_at":"2026-05-26T01:03:32.295555+00:00","updated_at":"2026-05-26T01:03:32.295555+00:00"}