{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GY3PAWCQCMUXLSJTNQA4XUVNMB","short_pith_number":"pith:GY3PAWCQ","schema_version":"1.0","canonical_sha256":"3636f05850132975c9336c01cbd2ad605c94c43f8709b2d46f7500e480e8bc0e","source":{"kind":"arxiv","id":"2011.13495","version":2},"attestation_state":"computed","paper":{"title":"Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Matthias Zwicker, Yu-Shen Liu, Zhizhong Han","submitted_at":"2020-11-26T23:18:10Z","abstract_excerpt":"Reconstructing continuous surfaces from 3D point clouds is a fundamental operation in 3D geometry processing. Several recent state-of-the-art methods address this problem using neural networks to learn signed distance functions (SDFs). In this paper, we introduce \\textit{Neural-Pull}, a new approach that is simple and leads to high quality SDFs. Specifically, we train a neural network to pull query 3D locations to their closest points on the surface using the predicted signed distance values and the gradient at the query locations, both of which are computed by the network itself. The pulling "},"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":"2011.13495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-26T23:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"0c7b744036a555b2b746e0df20f9a9ba73210e231a6f8a7efd517fb4b76ade57","abstract_canon_sha256":"8cae29612a3896f05966e0fa458f128e7390f8aed6b000bc7621098688851c72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:28.070495Z","signature_b64":"4G2+3bKsXOtCidoKDcDoig4rXUYaKDRWIMrA52uu0aMJX1FnyDnbcWOA+nerHnH6ch2NGF1cagmSiy8NrC7hCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3636f05850132975c9336c01cbd2ad605c94c43f8709b2d46f7500e480e8bc0e","last_reissued_at":"2026-07-05T02:42:28.070044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:28.070044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baorui Ma, Matthias Zwicker, Yu-Shen Liu, Zhizhong Han","submitted_at":"2020-11-26T23:18:10Z","abstract_excerpt":"Reconstructing continuous surfaces from 3D point clouds is a fundamental operation in 3D geometry processing. Several recent state-of-the-art methods address this problem using neural networks to learn signed distance functions (SDFs). In this paper, we introduce \\textit{Neural-Pull}, a new approach that is simple and leads to high quality SDFs. Specifically, we train a neural network to pull query 3D locations to their closest points on the surface using the predicted signed distance values and the gradient at the query locations, both of which are computed by the network itself. The pulling "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13495","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/2011.13495/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":"2011.13495","created_at":"2026-07-05T02:42:28.070098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.13495v2","created_at":"2026-07-05T02:42:28.070098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13495","created_at":"2026-07-05T02:42:28.070098+00:00"},{"alias_kind":"pith_short_12","alias_value":"GY3PAWCQCMUX","created_at":"2026-07-05T02:42:28.070098+00:00"},{"alias_kind":"pith_short_16","alias_value":"GY3PAWCQCMUXLSJT","created_at":"2026-07-05T02:42:28.070098+00:00"},{"alias_kind":"pith_short_8","alias_value":"GY3PAWCQ","created_at":"2026-07-05T02:42:28.070098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.14286","citing_title":"NeuralBoneReg: An Instance-Specific Label-Free Point Cloud-Based Method for Multi-Modal Bone Surface Registration","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16806","citing_title":"MedGS: Gaussian Splatting for Multi-Modal 3D Medical Imaging","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB","json":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB.json","graph_json":"https://pith.science/api/pith-number/GY3PAWCQCMUXLSJTNQA4XUVNMB/graph.json","events_json":"https://pith.science/api/pith-number/GY3PAWCQCMUXLSJTNQA4XUVNMB/events.json","paper":"https://pith.science/paper/GY3PAWCQ"},"agent_actions":{"view_html":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB","download_json":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB.json","view_paper":"https://pith.science/paper/GY3PAWCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.13495&json=true","fetch_graph":"https://pith.science/api/pith-number/GY3PAWCQCMUXLSJTNQA4XUVNMB/graph.json","fetch_events":"https://pith.science/api/pith-number/GY3PAWCQCMUXLSJTNQA4XUVNMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB/action/storage_attestation","attest_author":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB/action/author_attestation","sign_citation":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB/action/citation_signature","submit_replication":"https://pith.science/pith/GY3PAWCQCMUXLSJTNQA4XUVNMB/action/replication_record"}},"created_at":"2026-07-05T02:42:28.070098+00:00","updated_at":"2026-07-05T02:42:28.070098+00:00"}