{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NIHPXM4KLGNASI7XJIZLTYFDHD","short_pith_number":"pith:NIHPXM4K","schema_version":"1.0","canonical_sha256":"6a0efbb38a599a0923f74a32b9e0a338d6549a04909adc0c6c05f6b62c4a2c94","source":{"kind":"arxiv","id":"2403.06974","version":1},"attestation_state":"computed","paper":{"title":"Memory-based Adapters for Online 3D Scene Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Xia, Jie Zhou, Jiwen Lu, Linqing Zhao, Xiuwei Xu, Yueqi Duan, Ziwei Wang","submitted_at":"2024-03-11T17:57:41Z","abstract_excerpt":"In this paper, we propose a new framework for online 3D scene perception. Conventional 3D scene perception methods are offline, i.e., take an already reconstructed 3D scene geometry as input, which is not applicable in robotic applications where the input data is streaming RGB-D videos rather than a complete 3D scene reconstructed from pre-collected RGB-D videos. To deal with online 3D scene perception tasks where data collection and perception should be performed simultaneously, the model should be able to process 3D scenes frame by frame and make use of the temporal information. To this end,"},"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":"2403.06974","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:57:41Z","cross_cats_sorted":[],"title_canon_sha256":"9cd3c6a4ca7ab6f8b4414ddfdaec7378527f37f2af214857c4e6852e5f6777d9","abstract_canon_sha256":"ea714c80e0c3cb6c257aea65947b79dfb5920753260d6ca2dd768f434acb6a4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:45.335009Z","signature_b64":"6MHNxrfTcEVmqxyi0p9/Bun84/WTV8ZwdT9qtbQxCNnWLrey68M+9LAeH31P9BzZGXhiXiuVZ329STWedoRUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a0efbb38a599a0923f74a32b9e0a338d6549a04909adc0c6c05f6b62c4a2c94","last_reissued_at":"2026-07-05T07:54:45.334522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:45.334522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-based Adapters for Online 3D Scene Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Xia, Jie Zhou, Jiwen Lu, Linqing Zhao, Xiuwei Xu, Yueqi Duan, Ziwei Wang","submitted_at":"2024-03-11T17:57:41Z","abstract_excerpt":"In this paper, we propose a new framework for online 3D scene perception. Conventional 3D scene perception methods are offline, i.e., take an already reconstructed 3D scene geometry as input, which is not applicable in robotic applications where the input data is streaming RGB-D videos rather than a complete 3D scene reconstructed from pre-collected RGB-D videos. To deal with online 3D scene perception tasks where data collection and perception should be performed simultaneously, the model should be able to process 3D scenes frame by frame and make use of the temporal information. To this end,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06974","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/2403.06974/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":"2403.06974","created_at":"2026-07-05T07:54:45.334584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06974v1","created_at":"2026-07-05T07:54:45.334584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06974","created_at":"2026-07-05T07:54:45.334584+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIHPXM4KLGNA","created_at":"2026-07-05T07:54:45.334584+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIHPXM4KLGNASI7X","created_at":"2026-07-05T07:54:45.334584+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIHPXM4K","created_at":"2026-07-05T07:54:45.334584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04380","citing_title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD","json":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD.json","graph_json":"https://pith.science/api/pith-number/NIHPXM4KLGNASI7XJIZLTYFDHD/graph.json","events_json":"https://pith.science/api/pith-number/NIHPXM4KLGNASI7XJIZLTYFDHD/events.json","paper":"https://pith.science/paper/NIHPXM4K"},"agent_actions":{"view_html":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD","download_json":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD.json","view_paper":"https://pith.science/paper/NIHPXM4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06974&json=true","fetch_graph":"https://pith.science/api/pith-number/NIHPXM4KLGNASI7XJIZLTYFDHD/graph.json","fetch_events":"https://pith.science/api/pith-number/NIHPXM4KLGNASI7XJIZLTYFDHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD/action/storage_attestation","attest_author":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD/action/author_attestation","sign_citation":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD/action/citation_signature","submit_replication":"https://pith.science/pith/NIHPXM4KLGNASI7XJIZLTYFDHD/action/replication_record"}},"created_at":"2026-07-05T07:54:45.334584+00:00","updated_at":"2026-07-05T07:54:45.334584+00:00"}