{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NXNVBP3HRVICT3XXMNOXAVMKCH","short_pith_number":"pith:NXNVBP3H","schema_version":"1.0","canonical_sha256":"6ddb50bf678d5029eef7635d70558a11fd1dc5d7cd2ebfec553543426883bc67","source":{"kind":"arxiv","id":"2401.17857","version":4},"attestation_state":"computed","paper":{"title":"SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanchen Luo, Junran Peng, Junsong Fan, Lue Fan, Qing Li, Xu Hu, Yuxi Wang, Zhaoxiang Zhang, Zhen Lei","submitted_at":"2024-01-31T14:19:03Z","abstract_excerpt":"3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a "},"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":"2401.17857","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T14:19:03Z","cross_cats_sorted":[],"title_canon_sha256":"1ee25143420ef71976e4c9117ba1789ab403abd09dd8401f1096e75b57a0cb70","abstract_canon_sha256":"5b184d4e1002d68891833eb3a87d14370f620fe0c0e8d22ce4089bc765ddd84c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:43.520167Z","signature_b64":"ztM4q+yWXsomYI+lB19x9PZBhPBg3pISRaAHouJoRhlCB+mT5qe4r1EIpt9UEisAG/WhiVb7yRQ+pMyZnn4WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ddb50bf678d5029eef7635d70558a11fd1dc5d7cd2ebfec553543426883bc67","last_reissued_at":"2026-07-05T10:02:43.519697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:43.519697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanchen Luo, Junran Peng, Junsong Fan, Lue Fan, Qing Li, Xu Hu, Yuxi Wang, Zhaoxiang Zhang, Zhen Lei","submitted_at":"2024-01-31T14:19:03Z","abstract_excerpt":"3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis, benefiting from its high-quality rendering results and real-time rendering speed. However, the 3D Gaussians learned by 3D-GS have ambiguous structures without any geometry constraints. This inherent issue in 3D-GS leads to a rough boundary when segmenting individual objects. To remedy these problems, we propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS to improve segmentation accuracy while preserving segmentation speed. Specifically, we introduce a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17857","kind":"arxiv","version":4},"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/2401.17857/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":"2401.17857","created_at":"2026-07-05T10:02:43.519760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17857v4","created_at":"2026-07-05T10:02:43.519760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17857","created_at":"2026-07-05T10:02:43.519760+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXNVBP3HRVIC","created_at":"2026-07-05T10:02:43.519760+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXNVBP3HRVICT3XX","created_at":"2026-07-05T10:02:43.519760+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXNVBP3H","created_at":"2026-07-05T10:02:43.519760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01628","citing_title":"Online Segment 3D Gaussians via Launching Virtual Drones","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01708","citing_title":"Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04945","citing_title":"STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03890","citing_title":"A Survey on 3D Gaussian Splatting","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2412.09176","citing_title":"LIVE-GS: LLM Powers Interactive VR Experience with Physics-Aware Gaussian Splatting","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16065","citing_title":"Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27590","citing_title":"Fake3DGS: A Benchmark for 3D Manipulation Detection in Neural Rendering","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09662","citing_title":"BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05070","citing_title":"Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14706","citing_title":"NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH","json":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH.json","graph_json":"https://pith.science/api/pith-number/NXNVBP3HRVICT3XXMNOXAVMKCH/graph.json","events_json":"https://pith.science/api/pith-number/NXNVBP3HRVICT3XXMNOXAVMKCH/events.json","paper":"https://pith.science/paper/NXNVBP3H"},"agent_actions":{"view_html":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH","download_json":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH.json","view_paper":"https://pith.science/paper/NXNVBP3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17857&json=true","fetch_graph":"https://pith.science/api/pith-number/NXNVBP3HRVICT3XXMNOXAVMKCH/graph.json","fetch_events":"https://pith.science/api/pith-number/NXNVBP3HRVICT3XXMNOXAVMKCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH/action/storage_attestation","attest_author":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH/action/author_attestation","sign_citation":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH/action/citation_signature","submit_replication":"https://pith.science/pith/NXNVBP3HRVICT3XXMNOXAVMKCH/action/replication_record"}},"created_at":"2026-07-05T10:02:43.519760+00:00","updated_at":"2026-07-05T10:02:43.519760+00:00"}