{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VEXXCCUDDFV6IDAHKNCUNHF5DT","short_pith_number":"pith:VEXXCCUD","schema_version":"1.0","canonical_sha256":"a92f710a83196be40c075345469cbd1cd27566d6bd67b2e4923fd4770115e195","source":{"kind":"arxiv","id":"2506.15610","version":3},"attestation_state":"computed","paper":{"title":"BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Zhu, Jiazhao Zhang, Kai Xu, Renjiao Yi, Yihan Cao, Yijie Wang, Yuqing Lan, Zhirui Gao","submitted_at":"2025-06-18T16:40:05Z","abstract_excerpt":"Open-vocabulary 3D object detection has gained significant interest due to its critical applications in autonomous driving and embodied AI. Existing detection methods, whether offline or online, typically rely on dense point cloud reconstruction, which imposes substantial computational overhead and memory constraints, hindering real-time deployment in downstream tasks. To address this, we propose a novel reconstruction-free online framework tailored for memory-efficient and real-time 3D detection. Specifically, given streaming posed RGB-D video input, we leverage Cubify Anything as a pre-train"},"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":"2506.15610","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-18T16:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"d3fdf863f4e16688897f5eb94fd988502bd43fb044ec6c108873385d85efca2e","abstract_canon_sha256":"e035e9c963f4c20aeb1e77c645eb5dc12b0b50589011fd84bfa16a312b1b63be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:31.530196Z","signature_b64":"j47zJ5wcW4FOYaokhuBDmu/QCSLSxm6jxqSWgUTvdtR8du86dvTohQGY4yoKyjYUtFfrYGkixl2Yz9LuaeMtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a92f710a83196be40c075345469cbd1cd27566d6bd67b2e4923fd4770115e195","last_reissued_at":"2026-07-05T11:58:31.529762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:31.529762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenyang Zhu, Jiazhao Zhang, Kai Xu, Renjiao Yi, Yihan Cao, Yijie Wang, Yuqing Lan, Zhirui Gao","submitted_at":"2025-06-18T16:40:05Z","abstract_excerpt":"Open-vocabulary 3D object detection has gained significant interest due to its critical applications in autonomous driving and embodied AI. Existing detection methods, whether offline or online, typically rely on dense point cloud reconstruction, which imposes substantial computational overhead and memory constraints, hindering real-time deployment in downstream tasks. To address this, we propose a novel reconstruction-free online framework tailored for memory-efficient and real-time 3D detection. Specifically, given streaming posed RGB-D video input, we leverage Cubify Anything as a pre-train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15610","kind":"arxiv","version":3},"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/2506.15610/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":"2506.15610","created_at":"2026-07-05T11:58:31.529820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15610v3","created_at":"2026-07-05T11:58:31.529820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15610","created_at":"2026-07-05T11:58:31.529820+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEXXCCUDDFV6","created_at":"2026-07-05T11:58:31.529820+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEXXCCUDDFV6IDAH","created_at":"2026-07-05T11:58:31.529820+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEXXCCUD","created_at":"2026-07-05T11:58:31.529820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT","json":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT.json","graph_json":"https://pith.science/api/pith-number/VEXXCCUDDFV6IDAHKNCUNHF5DT/graph.json","events_json":"https://pith.science/api/pith-number/VEXXCCUDDFV6IDAHKNCUNHF5DT/events.json","paper":"https://pith.science/paper/VEXXCCUD"},"agent_actions":{"view_html":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT","download_json":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT.json","view_paper":"https://pith.science/paper/VEXXCCUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15610&json=true","fetch_graph":"https://pith.science/api/pith-number/VEXXCCUDDFV6IDAHKNCUNHF5DT/graph.json","fetch_events":"https://pith.science/api/pith-number/VEXXCCUDDFV6IDAHKNCUNHF5DT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT/action/storage_attestation","attest_author":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT/action/author_attestation","sign_citation":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT/action/citation_signature","submit_replication":"https://pith.science/pith/VEXXCCUDDFV6IDAHKNCUNHF5DT/action/replication_record"}},"created_at":"2026-07-05T11:58:31.529820+00:00","updated_at":"2026-07-05T11:58:31.529820+00:00"}