{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5Y5ANSUIONHDVX5S4BGTXFKRR7","short_pith_number":"pith:5Y5ANSUI","schema_version":"1.0","canonical_sha256":"ee3a06ca88734e3adfb2e04d3b95518ffe86ba4abc68ef1105c7be0399befe34","source":{"kind":"arxiv","id":"2503.08407","version":2},"attestation_state":"computed","paper":{"title":"WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Hu, Liujuan Cao, Yansong Guo, Yansong Qu","submitted_at":"2025-03-11T13:10:41Z","abstract_excerpt":"Recent advances in interactive 3D segmentation from 2D images have demonstrated impressive performance. However, current models typically require extensive scene-specific training to accurately reconstruct and segment objects, which limits their applicability in real-time scenarios. In this paper, we introduce WildSeg3D, an efficient approach that enables the segmentation of arbitrary 3D objects across diverse environments using a feed-forward mechanism. A key challenge of this feed-forward approach lies in the accumulation of 3D alignment errors across multiple 2D views, which can lead to ina"},"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":"2503.08407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T13:10:41Z","cross_cats_sorted":[],"title_canon_sha256":"0d52b8814e35258cf90e7a6dc5123963790913fcef5d57a24db204aff79f4e2f","abstract_canon_sha256":"3378b6161f30f658e6272a6908732580e90dcf0d33a7b0b6e23b2422eca03a4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:40.927641Z","signature_b64":"VOCjR7pEVf4xc1QKwT1XM4NEsLvYnqUT5iJLlCjgcAJcZuEIEm7sxWpbKzz8JB0J2s2u4L6kBSMCaqmVD+LtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee3a06ca88734e3adfb2e04d3b95518ffe86ba4abc68ef1105c7be0399befe34","last_reissued_at":"2026-07-05T10:32:40.926782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:40.926782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Hu, Liujuan Cao, Yansong Guo, Yansong Qu","submitted_at":"2025-03-11T13:10:41Z","abstract_excerpt":"Recent advances in interactive 3D segmentation from 2D images have demonstrated impressive performance. However, current models typically require extensive scene-specific training to accurately reconstruct and segment objects, which limits their applicability in real-time scenarios. In this paper, we introduce WildSeg3D, an efficient approach that enables the segmentation of arbitrary 3D objects across diverse environments using a feed-forward mechanism. A key challenge of this feed-forward approach lies in the accumulation of 3D alignment errors across multiple 2D views, which can lead to ina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08407","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/2503.08407/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":"2503.08407","created_at":"2026-07-05T10:32:40.926902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.08407v2","created_at":"2026-07-05T10:32:40.926902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08407","created_at":"2026-07-05T10:32:40.926902+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Y5ANSUIONHD","created_at":"2026-07-05T10:32:40.926902+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Y5ANSUIONHDVX5S","created_at":"2026-07-05T10:32:40.926902+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Y5ANSUI","created_at":"2026-07-05T10:32:40.926902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23777","citing_title":"XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7","json":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7.json","graph_json":"https://pith.science/api/pith-number/5Y5ANSUIONHDVX5S4BGTXFKRR7/graph.json","events_json":"https://pith.science/api/pith-number/5Y5ANSUIONHDVX5S4BGTXFKRR7/events.json","paper":"https://pith.science/paper/5Y5ANSUI"},"agent_actions":{"view_html":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7","download_json":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7.json","view_paper":"https://pith.science/paper/5Y5ANSUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.08407&json=true","fetch_graph":"https://pith.science/api/pith-number/5Y5ANSUIONHDVX5S4BGTXFKRR7/graph.json","fetch_events":"https://pith.science/api/pith-number/5Y5ANSUIONHDVX5S4BGTXFKRR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7/action/storage_attestation","attest_author":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7/action/author_attestation","sign_citation":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7/action/citation_signature","submit_replication":"https://pith.science/pith/5Y5ANSUIONHDVX5S4BGTXFKRR7/action/replication_record"}},"created_at":"2026-07-05T10:32:40.926902+00:00","updated_at":"2026-07-05T10:32:40.926902+00:00"}