{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VLDA7YQSUHMMTTWCANC2TI3BYI","short_pith_number":"pith:VLDA7YQS","schema_version":"1.0","canonical_sha256":"aac60fe212a1d8c9cec20345a9a361c21c1012956425fef1b383133005ee37cf","source":{"kind":"arxiv","id":"2211.13067","version":1},"attestation_state":"computed","paper":{"title":"Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Tianyu Wang, Xiaowei Hu, Zhengzhe Liu","submitted_at":"2022-11-23T16:01:06Z","abstract_excerpt":"LiDAR-produced point clouds are the major source for most state-of-the-art 3D object detectors. Yet, small, distant, and incomplete objects with sparse or few points are often hard to detect. We present Sparse2Dense, a new framework to efficiently boost 3D detection performance by learning to densify point clouds in latent space. Specifically, we first train a dense point 3D detector (DDet) with a dense point cloud as input and design a sparse point 3D detector (SDet) with a regular point cloud as input. Importantly, we formulate the lightweight plug-in S2D module and the point cloud reconstru"},"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":"2211.13067","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-23T16:01:06Z","cross_cats_sorted":[],"title_canon_sha256":"01b7a76b637d5fc1ac89e09c2276c061342280b9978961b5e6b2b6f8aa7b87cd","abstract_canon_sha256":"9928822fa9469c59fe26488702d9c7f151f23163faddfaaa1f12d2a75d400966"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:58.061304Z","signature_b64":"DSgK40U6wEwijAC6PvNdTbO+pbN/wKPDLRrRaJoIG0Z60xbb7q+Jjxq4101hdl/aZ0yck/9zgKavwY7bTSX3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac60fe212a1d8c9cec20345a9a361c21c1012956425fef1b383133005ee37cf","last_reissued_at":"2026-07-05T05:18:58.060842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:58.060842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Tianyu Wang, Xiaowei Hu, Zhengzhe Liu","submitted_at":"2022-11-23T16:01:06Z","abstract_excerpt":"LiDAR-produced point clouds are the major source for most state-of-the-art 3D object detectors. Yet, small, distant, and incomplete objects with sparse or few points are often hard to detect. We present Sparse2Dense, a new framework to efficiently boost 3D detection performance by learning to densify point clouds in latent space. Specifically, we first train a dense point 3D detector (DDet) with a dense point cloud as input and design a sparse point 3D detector (SDet) with a regular point cloud as input. Importantly, we formulate the lightweight plug-in S2D module and the point cloud reconstru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13067","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/2211.13067/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":"2211.13067","created_at":"2026-07-05T05:18:58.060899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13067v1","created_at":"2026-07-05T05:18:58.060899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13067","created_at":"2026-07-05T05:18:58.060899+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLDA7YQSUHMM","created_at":"2026-07-05T05:18:58.060899+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLDA7YQSUHMMTTWC","created_at":"2026-07-05T05:18:58.060899+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLDA7YQS","created_at":"2026-07-05T05:18:58.060899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13788","citing_title":"RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI","json":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI.json","graph_json":"https://pith.science/api/pith-number/VLDA7YQSUHMMTTWCANC2TI3BYI/graph.json","events_json":"https://pith.science/api/pith-number/VLDA7YQSUHMMTTWCANC2TI3BYI/events.json","paper":"https://pith.science/paper/VLDA7YQS"},"agent_actions":{"view_html":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI","download_json":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI.json","view_paper":"https://pith.science/paper/VLDA7YQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13067&json=true","fetch_graph":"https://pith.science/api/pith-number/VLDA7YQSUHMMTTWCANC2TI3BYI/graph.json","fetch_events":"https://pith.science/api/pith-number/VLDA7YQSUHMMTTWCANC2TI3BYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI/action/storage_attestation","attest_author":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI/action/author_attestation","sign_citation":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI/action/citation_signature","submit_replication":"https://pith.science/pith/VLDA7YQSUHMMTTWCANC2TI3BYI/action/replication_record"}},"created_at":"2026-07-05T05:18:58.060899+00:00","updated_at":"2026-07-05T05:18:58.060899+00:00"}