{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LDLEDUTIX42HCSSY4TLUTN2RHT","short_pith_number":"pith:LDLEDUTI","schema_version":"1.0","canonical_sha256":"58d641d268bf34714a58e4d749b7513cc0ec358cb10daf54ac8f012513e0821d","source":{"kind":"arxiv","id":"2108.07506","version":1},"attestation_state":"computed","paper":{"title":"PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haitian Zeng, Xiaohan Wang, Xin Yu, Yi Yang, Yuchao Dai","submitted_at":"2021-08-17T08:39:02Z","abstract_excerpt":"We propose PR-RRN, a novel neural-network based method for Non-rigid Structure-from-Motion (NRSfM). PR-RRN consists of Residual-Recursive Networks (RRN) and two extra regularization losses. RRN is designed to effectively recover 3D shape and camera from 2D keypoints with novel residual-recursive structure. As NRSfM is a highly under-constrained problem, we propose two new pairwise regularization to further regularize the reconstruction. The Rigidity-based Pairwise Contrastive Loss regularizes the shape representation by encouraging higher similarity between the representations of high-rigidity"},"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":"2108.07506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-17T08:39:02Z","cross_cats_sorted":[],"title_canon_sha256":"df62183e157ab761e1790eca07ccfb5d1d9804eff48d02d3cb1880c13a3fc646","abstract_canon_sha256":"f3e44880e5e11238723c87cc4defe94d101e72674c152abc1f6186340ce3337e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:39.704330Z","signature_b64":"aX6wsiTN3h0M4hAaXIGx0yLgLkCtvbBjXV1i9yODop4J/F0jUHcQOTBNmLvFLRBE5ED+1/PeZKWwh7JdpFlUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58d641d268bf34714a58e4d749b7513cc0ec358cb10daf54ac8f012513e0821d","last_reissued_at":"2026-07-05T03:06:39.703755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:39.703755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haitian Zeng, Xiaohan Wang, Xin Yu, Yi Yang, Yuchao Dai","submitted_at":"2021-08-17T08:39:02Z","abstract_excerpt":"We propose PR-RRN, a novel neural-network based method for Non-rigid Structure-from-Motion (NRSfM). PR-RRN consists of Residual-Recursive Networks (RRN) and two extra regularization losses. RRN is designed to effectively recover 3D shape and camera from 2D keypoints with novel residual-recursive structure. As NRSfM is a highly under-constrained problem, we propose two new pairwise regularization to further regularize the reconstruction. The Rigidity-based Pairwise Contrastive Loss regularizes the shape representation by encouraging higher similarity between the representations of high-rigidity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07506","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/2108.07506/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":"2108.07506","created_at":"2026-07-05T03:06:39.703816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.07506v1","created_at":"2026-07-05T03:06:39.703816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07506","created_at":"2026-07-05T03:06:39.703816+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDLEDUTIX42H","created_at":"2026-07-05T03:06:39.703816+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDLEDUTIX42HCSSY","created_at":"2026-07-05T03:06:39.703816+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDLEDUTI","created_at":"2026-07-05T03:06:39.703816+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/LDLEDUTIX42HCSSY4TLUTN2RHT","json":"https://pith.science/pith/LDLEDUTIX42HCSSY4TLUTN2RHT.json","graph_json":"https://pith.science/api/pith-number/LDLEDUTIX42HCSSY4TLUTN2RHT/graph.json","events_json":"https://pith.science/api/pith-number/LDLEDUTIX42HCSSY4TLUTN2RHT/events.json","paper":"https://pith.science/paper/LDLEDUTI"},"agent_actions":{"view_html":"https://pith.science/pith/LDLEDUTIX42HCSSY4TLUTN2RHT","download_json":"https://pith.science/pith/LDLEDUTIX42HCSSY4TLUTN2RHT.json","view_paper":"https://pith.science/paper/LDLEDUTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.07506&json=true","fetch_graph":"https://pith.science/api/pith-number/LDLEDUTIX42HCSSY4TLUTN2RHT/graph.json","fetch_events":"https://pith.science/api/pith-number/LDLEDUTIX42HCSSY4TLUTN2RHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDLEDUTIX42HCSSY4TLUTN2RHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDLEDUTIX42HCSSY4TLUTN2RHT/action/storage_attestation","attest_author":"https://pith.science/pith/LDLEDUTIX42HCSSY4TLUTN2RHT/action/author_attestation","sign_citation":"https://pith.science/pith/LDLEDUTIX42HCSSY4TLUTN2RHT/action/citation_signature","submit_replication":"https://pith.science/pith/LDLEDUTIX42HCSSY4TLUTN2RHT/action/replication_record"}},"created_at":"2026-07-05T03:06:39.703816+00:00","updated_at":"2026-07-05T03:06:39.703816+00:00"}