{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:75E4WVQQTCLECTRCXV353BZK66","short_pith_number":"pith:75E4WVQQ","schema_version":"1.0","canonical_sha256":"ff49cb56109896414e22bd77dd872af7a27ab6c632d4780c2702d60c8dcfbe20","source":{"kind":"arxiv","id":"2306.13631","version":2},"attestation_state":"computed","paper":{"title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ay\\c{c}a Takmaz, Elisabetta Fedele, Federico Tombari, Francis Engelmann, Marc Pollefeys, Robert W. Sumner","submitted_at":"2023-06-23T17:36:44Z","abstract_excerpt":"We introduce the task of open-vocabulary 3D instance segmentation. Current approaches for 3D instance segmentation can typically only recognize object categories from a pre-defined closed set of classes that are annotated in the training datasets. This results in important limitations for real-world applications where one might need to perform tasks guided by novel, open-vocabulary queries related to a wide variety of objects. Recently, open-vocabulary 3D scene understanding methods have emerged to address this problem by learning queryable features for each point in the scene. While such a re"},"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":"2306.13631","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-23T17:36:44Z","cross_cats_sorted":[],"title_canon_sha256":"11fd812e190acb8b6339cd625e08d8c3ec9ce1a848ffdaeda7e7a1b67673566f","abstract_canon_sha256":"5c20a0901852b87aa9d1f7f8848272e2eb86e73660bbfb626c049db4ac2f9c51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:30.617235Z","signature_b64":"As/7bR/VMY9Zxl5Klp/p5FJ83T76XsMXQeJGz/t9eYwF4pkBwbfEKt2FJAIPMuCCHC6Ni1qFm6GKp8OjADQDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff49cb56109896414e22bd77dd872af7a27ab6c632d4780c2702d60c8dcfbe20","last_reissued_at":"2026-07-05T07:06:30.616721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:30.616721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ay\\c{c}a Takmaz, Elisabetta Fedele, Federico Tombari, Francis Engelmann, Marc Pollefeys, Robert W. Sumner","submitted_at":"2023-06-23T17:36:44Z","abstract_excerpt":"We introduce the task of open-vocabulary 3D instance segmentation. Current approaches for 3D instance segmentation can typically only recognize object categories from a pre-defined closed set of classes that are annotated in the training datasets. This results in important limitations for real-world applications where one might need to perform tasks guided by novel, open-vocabulary queries related to a wide variety of objects. Recently, open-vocabulary 3D scene understanding methods have emerged to address this problem by learning queryable features for each point in the scene. While such a re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13631","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/2306.13631/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":"2306.13631","created_at":"2026-07-05T07:06:30.616796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13631v2","created_at":"2026-07-05T07:06:30.616796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13631","created_at":"2026-07-05T07:06:30.616796+00:00"},{"alias_kind":"pith_short_12","alias_value":"75E4WVQQTCLE","created_at":"2026-07-05T07:06:30.616796+00:00"},{"alias_kind":"pith_short_16","alias_value":"75E4WVQQTCLECTRC","created_at":"2026-07-05T07:06:30.616796+00:00"},{"alias_kind":"pith_short_8","alias_value":"75E4WVQQ","created_at":"2026-07-05T07:06:30.616796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05955","citing_title":"NegROI: Click-Centric Uncertainty-Guided Refinement with Scene-Conditioned Negative Prompts for Robust Interactive 3D Segmentation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24068","citing_title":"ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21292","citing_title":"Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10594","citing_title":"Segment and Select: Vision-Language Segmentation in 3D Scenarios","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07280","citing_title":"Geometric-Aware Hypergraph Reasoning for Novel Class Discovery in Point Cloud Segmentation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30638","citing_title":"Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25901","citing_title":"AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26831","citing_title":"OSMa-Bench++: Toward Open-Ended Benchmarking of Semantic Mapping for Manipulation with Prompt-Generated Synthetic Scenes","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06239","citing_title":"Open-Architecture End-to-End System for Real-World Autonomous Robot Navigation","ref_index":14,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08925","citing_title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16832","citing_title":"Coarse Semantic Injection for LLM-Conditioned Structured Indoor Prediction","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03370","citing_title":"ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03532","citing_title":"OpenTrack3D: Towards Accurate and Generalizable Open-Vocabulary 3D Instance Segmentation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2601.08831","citing_title":"3AM: 3egment Anything with Geometric Consistency in Videos","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08096","citing_title":"TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20530","citing_title":"Memory Over Maps: 3D Object Localization Without Reconstruction","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08925","citing_title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08916","citing_title":"MV3DIS: Multi-View Mask Matching via 3D Guides for Zero-Shot 3D Instance Segmentation","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66","json":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66.json","graph_json":"https://pith.science/api/pith-number/75E4WVQQTCLECTRCXV353BZK66/graph.json","events_json":"https://pith.science/api/pith-number/75E4WVQQTCLECTRCXV353BZK66/events.json","paper":"https://pith.science/paper/75E4WVQQ"},"agent_actions":{"view_html":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66","download_json":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66.json","view_paper":"https://pith.science/paper/75E4WVQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13631&json=true","fetch_graph":"https://pith.science/api/pith-number/75E4WVQQTCLECTRCXV353BZK66/graph.json","fetch_events":"https://pith.science/api/pith-number/75E4WVQQTCLECTRCXV353BZK66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66/action/storage_attestation","attest_author":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66/action/author_attestation","sign_citation":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66/action/citation_signature","submit_replication":"https://pith.science/pith/75E4WVQQTCLECTRCXV353BZK66/action/replication_record"}},"created_at":"2026-07-05T07:06:30.616796+00:00","updated_at":"2026-07-05T07:06:30.616796+00:00"}