{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZRPRFT2WLZQDMCHU22RH5UFMQJ","short_pith_number":"pith:ZRPRFT2W","schema_version":"1.0","canonical_sha256":"cc5f12cf565e603608f4d6a27ed0ac8262ca5b97c928db4887ceff64f969d28a","source":{"kind":"arxiv","id":"2312.03053","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Multi-step Refinement Network for Robust Point Cloud Registration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mathieu Salzmann, Sabine S\\\"usstrunk, Tong Zhang, Wenbing Tao, Yufan Ren, Zheng Dang, Zhi Chen","submitted_at":"2023-12-05T18:59:41Z","abstract_excerpt":"Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds of the same scene. Despite significant progress with learning-based approaches, existing methods still face challenges when the overlapping region between the two point clouds is small. In this paper, we propose an adaptive multi-step refinement network that refines the registration quality at each step by leveraging the information from the preceding step. To achieve this, we introduce a training procedure and a refinement network. Firstly, to adapt the network to the current step, we utilize a"},"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":"2312.03053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T18:59:41Z","cross_cats_sorted":[],"title_canon_sha256":"f1ab7db7e3989a2ddf9502a0a3a0a5296054f58b3cd525e537abde6c5a2f65ed","abstract_canon_sha256":"5361b60503fe31b399b34b37a7387f5950a364abd2d9cbd9cc5f868baf9943c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:44.957621Z","signature_b64":"RhG3hQatl2nVR+qFq4OttsDC+je3bVWJv8l4ppvQtLaheoai5K2mGAgIbKG7pvA9UGNovOg6mxMFzbCExovFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc5f12cf565e603608f4d6a27ed0ac8262ca5b97c928db4887ceff64f969d28a","last_reissued_at":"2026-07-05T10:41:44.957147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:44.957147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Multi-step Refinement Network for Robust Point Cloud Registration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mathieu Salzmann, Sabine S\\\"usstrunk, Tong Zhang, Wenbing Tao, Yufan Ren, Zheng Dang, Zhi Chen","submitted_at":"2023-12-05T18:59:41Z","abstract_excerpt":"Point Cloud Registration (PCR) estimates the relative rigid transformation between two point clouds of the same scene. Despite significant progress with learning-based approaches, existing methods still face challenges when the overlapping region between the two point clouds is small. In this paper, we propose an adaptive multi-step refinement network that refines the registration quality at each step by leveraging the information from the preceding step. To achieve this, we introduce a training procedure and a refinement network. Firstly, to adapt the network to the current step, we utilize a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03053","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/2312.03053/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":"2312.03053","created_at":"2026-07-05T10:41:44.957205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03053v2","created_at":"2026-07-05T10:41:44.957205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03053","created_at":"2026-07-05T10:41:44.957205+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRPRFT2WLZQD","created_at":"2026-07-05T10:41:44.957205+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRPRFT2WLZQDMCHU","created_at":"2026-07-05T10:41:44.957205+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRPRFT2W","created_at":"2026-07-05T10:41:44.957205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.00436","citing_title":"Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13183","citing_title":"MT-PCR: Hybrid Mamba-Transformer Network with Spatial Serialization for Point Cloud Registration","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ","json":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ.json","graph_json":"https://pith.science/api/pith-number/ZRPRFT2WLZQDMCHU22RH5UFMQJ/graph.json","events_json":"https://pith.science/api/pith-number/ZRPRFT2WLZQDMCHU22RH5UFMQJ/events.json","paper":"https://pith.science/paper/ZRPRFT2W"},"agent_actions":{"view_html":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ","download_json":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ.json","view_paper":"https://pith.science/paper/ZRPRFT2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03053&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRPRFT2WLZQDMCHU22RH5UFMQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRPRFT2WLZQDMCHU22RH5UFMQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZRPRFT2WLZQDMCHU22RH5UFMQJ/action/replication_record"}},"created_at":"2026-07-05T10:41:44.957205+00:00","updated_at":"2026-07-05T10:41:44.957205+00:00"}