{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H3ZIOPLPY4UPARON7SF2Y6VJWO","short_pith_number":"pith:H3ZIOPLP","schema_version":"1.0","canonical_sha256":"3ef2873d6fc728f045cdfc8bac7aa9b385af06fb178dfe894adab6d844e955f1","source":{"kind":"arxiv","id":"2311.17707","version":2},"attestation_state":"computed","paper":{"title":"SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingteng Qiu, Mutian Xu, Xiaoguang Han, Xingyilang Yin, Xin Tong, Yang Liu","submitted_at":"2023-11-29T15:11:03Z","abstract_excerpt":"We introduce SAMPro3D for zero-shot instance segmentation of 3D scenes. Given the 3D point cloud and multiple posed RGB-D frames of 3D scenes, our approach segments 3D instances by applying the pretrained Segment Anything Model (SAM) to 2D frames. Our key idea involves locating SAM prompts in 3D to align their projected pixel prompts across frames, ensuring the view consistency of SAM-predicted masks. Moreover, we suggest selecting prompts from the initial set guided by the information of SAM-predicted masks across all views, which enhances the overall performance. We further propose to consol"},"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":"2311.17707","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-29T15:11:03Z","cross_cats_sorted":[],"title_canon_sha256":"ff1e956c4b4efd31d767edf0c07b110ee282707b9cda8050129ad760073c3e9c","abstract_canon_sha256":"adf0964b87ef58da9ab565e3dd19eedcc2724c89d9932d8ce4d043f8e035b40d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:01.376236Z","signature_b64":"2crC/RTgVi+2ZChdHSxEOjpFSI7aQJe9tzhXDLWdz0xi+CZ7GVWG2+tLxi0NTH/Nfg4DCrf6RQ/VWV+oZwWwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ef2873d6fc728f045cdfc8bac7aa9b385af06fb178dfe894adab6d844e955f1","last_reissued_at":"2026-07-05T10:09:01.375674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:01.375674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingteng Qiu, Mutian Xu, Xiaoguang Han, Xingyilang Yin, Xin Tong, Yang Liu","submitted_at":"2023-11-29T15:11:03Z","abstract_excerpt":"We introduce SAMPro3D for zero-shot instance segmentation of 3D scenes. Given the 3D point cloud and multiple posed RGB-D frames of 3D scenes, our approach segments 3D instances by applying the pretrained Segment Anything Model (SAM) to 2D frames. Our key idea involves locating SAM prompts in 3D to align their projected pixel prompts across frames, ensuring the view consistency of SAM-predicted masks. Moreover, we suggest selecting prompts from the initial set guided by the information of SAM-predicted masks across all views, which enhances the overall performance. We further propose to consol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17707","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/2311.17707/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":"2311.17707","created_at":"2026-07-05T10:09:01.375740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17707v2","created_at":"2026-07-05T10:09:01.375740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17707","created_at":"2026-07-05T10:09:01.375740+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3ZIOPLPY4UP","created_at":"2026-07-05T10:09:01.375740+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3ZIOPLPY4UPARON","created_at":"2026-07-05T10:09:01.375740+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3ZIOPLP","created_at":"2026-07-05T10:09:01.375740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29376","citing_title":"SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29505","citing_title":"ESAM++: Efficient Online 3D Perception on the Edge","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08925","citing_title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03370","citing_title":"ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08925","citing_title":"ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO","json":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO.json","graph_json":"https://pith.science/api/pith-number/H3ZIOPLPY4UPARON7SF2Y6VJWO/graph.json","events_json":"https://pith.science/api/pith-number/H3ZIOPLPY4UPARON7SF2Y6VJWO/events.json","paper":"https://pith.science/paper/H3ZIOPLP"},"agent_actions":{"view_html":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO","download_json":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO.json","view_paper":"https://pith.science/paper/H3ZIOPLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17707&json=true","fetch_graph":"https://pith.science/api/pith-number/H3ZIOPLPY4UPARON7SF2Y6VJWO/graph.json","fetch_events":"https://pith.science/api/pith-number/H3ZIOPLPY4UPARON7SF2Y6VJWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO/action/storage_attestation","attest_author":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO/action/author_attestation","sign_citation":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO/action/citation_signature","submit_replication":"https://pith.science/pith/H3ZIOPLPY4UPARON7SF2Y6VJWO/action/replication_record"}},"created_at":"2026-07-05T10:09:01.375740+00:00","updated_at":"2026-07-05T10:09:01.375740+00:00"}