{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VHWUBHBXBGMMFYW2CX74U7C6EP","short_pith_number":"pith:VHWUBHBX","schema_version":"1.0","canonical_sha256":"a9ed409c370998c2e2da15ffca7c5e23d5b6b518ca3556db273461c0b516e62b","source":{"kind":"arxiv","id":"2412.00392","version":1},"attestation_state":"computed","paper":{"title":"GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baolong Bi, Hao Jiang, Honglong Zhao, Shuqin Gao, Wenwei Han, Yujun Cai, Zehao Li, Zhaoqi Wang","submitted_at":"2024-11-30T08:07:37Z","abstract_excerpt":"While 3D Gaussian Splatting enables high-quality real-time rendering, existing Gaussian-based frameworks for 3D semantic segmentation still face significant challenges in boundary recognition accuracy. To address this, we propose a novel 3DGS-based framework named GradiSeg, incorporating Identity Encoding to construct a deeper semantic understanding of scenes. Our approach introduces two key modules: Identity Gradient Guided Densification (IGD) and Local Adaptive K-Nearest Neighbors (LA-KNN). The IGD module supervises gradients of Identity Encoding to refine Gaussian distributions along object"},"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":"2412.00392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-30T08:07:37Z","cross_cats_sorted":[],"title_canon_sha256":"3414ef1660d8f9274e89430a20c11340f3ce8b5f9103987298222a07ec8e966d","abstract_canon_sha256":"8bec5ac78cc0055099f7a12af18488779d0c556707564ccb857591254aee4b7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:40.618173Z","signature_b64":"yFkRZdrWNdP2efed6LlTQUqro/t9Dw3XXazLjamWjOLP4pddvfLF9yBgb2wHdoDk2w2y0ItDKsC7yxfiy61lDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9ed409c370998c2e2da15ffca7c5e23d5b6b518ca3556db273461c0b516e62b","last_reissued_at":"2026-07-05T09:42:40.617663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:40.617663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baolong Bi, Hao Jiang, Honglong Zhao, Shuqin Gao, Wenwei Han, Yujun Cai, Zehao Li, Zhaoqi Wang","submitted_at":"2024-11-30T08:07:37Z","abstract_excerpt":"While 3D Gaussian Splatting enables high-quality real-time rendering, existing Gaussian-based frameworks for 3D semantic segmentation still face significant challenges in boundary recognition accuracy. To address this, we propose a novel 3DGS-based framework named GradiSeg, incorporating Identity Encoding to construct a deeper semantic understanding of scenes. Our approach introduces two key modules: Identity Gradient Guided Densification (IGD) and Local Adaptive K-Nearest Neighbors (LA-KNN). The IGD module supervises gradients of Identity Encoding to refine Gaussian distributions along object"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00392","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/2412.00392/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":"2412.00392","created_at":"2026-07-05T09:42:40.617721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00392v1","created_at":"2026-07-05T09:42:40.617721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00392","created_at":"2026-07-05T09:42:40.617721+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHWUBHBXBGMM","created_at":"2026-07-05T09:42:40.617721+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHWUBHBXBGMMFYW2","created_at":"2026-07-05T09:42:40.617721+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHWUBHBX","created_at":"2026-07-05T09:42:40.617721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.13215","citing_title":"DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2508.09977","citing_title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19172","citing_title":"MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP","json":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP.json","graph_json":"https://pith.science/api/pith-number/VHWUBHBXBGMMFYW2CX74U7C6EP/graph.json","events_json":"https://pith.science/api/pith-number/VHWUBHBXBGMMFYW2CX74U7C6EP/events.json","paper":"https://pith.science/paper/VHWUBHBX"},"agent_actions":{"view_html":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP","download_json":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP.json","view_paper":"https://pith.science/paper/VHWUBHBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00392&json=true","fetch_graph":"https://pith.science/api/pith-number/VHWUBHBXBGMMFYW2CX74U7C6EP/graph.json","fetch_events":"https://pith.science/api/pith-number/VHWUBHBXBGMMFYW2CX74U7C6EP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP/action/storage_attestation","attest_author":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP/action/author_attestation","sign_citation":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP/action/citation_signature","submit_replication":"https://pith.science/pith/VHWUBHBXBGMMFYW2CX74U7C6EP/action/replication_record"}},"created_at":"2026-07-05T09:42:40.617721+00:00","updated_at":"2026-07-05T09:42:40.617721+00:00"}