{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZWDUAKBAULPLBLFCUE2FH5QKH6","short_pith_number":"pith:ZWDUAKBA","schema_version":"1.0","canonical_sha256":"cd87402820a2deb0aca2a13453f60a3fabe65199668d037ee6670b4f87c9d7d5","source":{"kind":"arxiv","id":"2506.12400","version":2},"attestation_state":"computed","paper":{"title":"Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbi Zhou, Zhangkai Ni","submitted_at":"2025-06-14T08:31:53Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis. However, existing methods struggle to adaptively optimize the distribution of Gaussian primitives based on scene characteristics, making it challenging to balance reconstruction quality and efficiency. Inspired by human perception, we propose scene-adaptive perceptual densification for Gaussian Splatting (Perceptual-GS), a novel framework that integrates perceptual sensitivity into the 3DGS training process to address this challenge. We first introduce a perception-aware representation that models human "},"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":"2506.12400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-14T08:31:53Z","cross_cats_sorted":[],"title_canon_sha256":"00a560d567e9406b78e8ab6aeaff37a4b159c40f51a853e91600ff79a495eabf","abstract_canon_sha256":"d6d9d6b20ff2c66cdd41b2df6571fa17d609c173430f7f66e59885c2cfb443dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:53.585042Z","signature_b64":"KoZYVuQb4gGFJ8FSDAOCWJEw6Sqkag4wuCW8Bs2K9QYy/bVgG/GLTZ+qIWydK1Wj6b4t81AtEb1K2pIlyYXdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd87402820a2deb0aca2a13453f60a3fabe65199668d037ee6670b4f87c9d7d5","last_reissued_at":"2026-07-05T11:24:53.584566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:53.584566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbi Zhou, Zhangkai Ni","submitted_at":"2025-06-14T08:31:53Z","abstract_excerpt":"3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis. However, existing methods struggle to adaptively optimize the distribution of Gaussian primitives based on scene characteristics, making it challenging to balance reconstruction quality and efficiency. Inspired by human perception, we propose scene-adaptive perceptual densification for Gaussian Splatting (Perceptual-GS), a novel framework that integrates perceptual sensitivity into the 3DGS training process to address this challenge. We first introduce a perception-aware representation that models human "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12400","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/2506.12400/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":"2506.12400","created_at":"2026-07-05T11:24:53.584624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12400v2","created_at":"2026-07-05T11:24:53.584624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12400","created_at":"2026-07-05T11:24:53.584624+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWDUAKBAULPL","created_at":"2026-07-05T11:24:53.584624+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWDUAKBAULPLBLFC","created_at":"2026-07-05T11:24:53.584624+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWDUAKBA","created_at":"2026-07-05T11:24:53.584624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05155","citing_title":"Aes3D: Aesthetic Assessment in 3D Gaussian Splatting","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26238","citing_title":"EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00408","citing_title":"Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05155","citing_title":"Aes3D: Aesthetic Assessment in 3D Gaussian Splatting","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00408","citing_title":"Beyond Heuristics: Learnable Density Control for 3D Gaussian Splatting","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21400","citing_title":"You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6","json":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6.json","graph_json":"https://pith.science/api/pith-number/ZWDUAKBAULPLBLFCUE2FH5QKH6/graph.json","events_json":"https://pith.science/api/pith-number/ZWDUAKBAULPLBLFCUE2FH5QKH6/events.json","paper":"https://pith.science/paper/ZWDUAKBA"},"agent_actions":{"view_html":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6","download_json":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6.json","view_paper":"https://pith.science/paper/ZWDUAKBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12400&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWDUAKBAULPLBLFCUE2FH5QKH6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWDUAKBAULPLBLFCUE2FH5QKH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6/action/storage_attestation","attest_author":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6/action/author_attestation","sign_citation":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6/action/citation_signature","submit_replication":"https://pith.science/pith/ZWDUAKBAULPLBLFCUE2FH5QKH6/action/replication_record"}},"created_at":"2026-07-05T11:24:53.584624+00:00","updated_at":"2026-07-05T11:24:53.584624+00:00"}