{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:POAHB5QZXIWSQ6NHIP3SV4YXR4","short_pith_number":"pith:POAHB5QZ","schema_version":"1.0","canonical_sha256":"7b8070f619ba2d2879a743f72af3178f112ea80e32f43ba0a75e348bfba862ce","source":{"kind":"arxiv","id":"2008.13504","version":2},"attestation_state":"computed","paper":{"title":"Deep Probabilistic Feature-metric Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrew J. Davison, Binbin Xu, Stefan Leutenegger","submitted_at":"2020-08-31T11:47:59Z","abstract_excerpt":"Dense image alignment from RGB-D images remains a critical issue for real-world applications, especially under challenging lighting conditions and in a wide baseline setting. In this paper, we propose a new framework to learn a pixel-wise deep feature map and a deep feature-metric uncertainty map predicted by a Convolutional Neural Network (CNN), which together formulate a deep probabilistic feature-metric residual of the two-view constraint that can be minimised using Gauss-Newton in a coarse-to-fine optimisation framework. Furthermore, our network predicts a deep initial pose for faster and "},"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":"2008.13504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-31T11:47:59Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"0da3c797660f73e83323c08f85a5aefb38a2bf8736ea0c8236183adae7219d13","abstract_canon_sha256":"ea7d5a7c3f0e42dcfa172f8147b805712b24832106e70adbad0a8eb2709144b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:54:46.736533Z","signature_b64":"OJMyHpqS347zWMirZ2KpioNI7JxafNZxztlxVu8XDX9aRpxrPr+c7qtPwIuncXKrybIfYBWo2DcHyxZ+kxdwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b8070f619ba2d2879a743f72af3178f112ea80e32f43ba0a75e348bfba862ce","last_reissued_at":"2026-07-05T01:54:46.736019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:54:46.736019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Probabilistic Feature-metric Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Andrew J. Davison, Binbin Xu, Stefan Leutenegger","submitted_at":"2020-08-31T11:47:59Z","abstract_excerpt":"Dense image alignment from RGB-D images remains a critical issue for real-world applications, especially under challenging lighting conditions and in a wide baseline setting. In this paper, we propose a new framework to learn a pixel-wise deep feature map and a deep feature-metric uncertainty map predicted by a Convolutional Neural Network (CNN), which together formulate a deep probabilistic feature-metric residual of the two-view constraint that can be minimised using Gauss-Newton in a coarse-to-fine optimisation framework. Furthermore, our network predicts a deep initial pose for faster and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.13504","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/2008.13504/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":"2008.13504","created_at":"2026-07-05T01:54:46.736077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.13504v2","created_at":"2026-07-05T01:54:46.736077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.13504","created_at":"2026-07-05T01:54:46.736077+00:00"},{"alias_kind":"pith_short_12","alias_value":"POAHB5QZXIWS","created_at":"2026-07-05T01:54:46.736077+00:00"},{"alias_kind":"pith_short_16","alias_value":"POAHB5QZXIWSQ6NH","created_at":"2026-07-05T01:54:46.736077+00:00"},{"alias_kind":"pith_short_8","alias_value":"POAHB5QZ","created_at":"2026-07-05T01:54:46.736077+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/POAHB5QZXIWSQ6NHIP3SV4YXR4","json":"https://pith.science/pith/POAHB5QZXIWSQ6NHIP3SV4YXR4.json","graph_json":"https://pith.science/api/pith-number/POAHB5QZXIWSQ6NHIP3SV4YXR4/graph.json","events_json":"https://pith.science/api/pith-number/POAHB5QZXIWSQ6NHIP3SV4YXR4/events.json","paper":"https://pith.science/paper/POAHB5QZ"},"agent_actions":{"view_html":"https://pith.science/pith/POAHB5QZXIWSQ6NHIP3SV4YXR4","download_json":"https://pith.science/pith/POAHB5QZXIWSQ6NHIP3SV4YXR4.json","view_paper":"https://pith.science/paper/POAHB5QZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.13504&json=true","fetch_graph":"https://pith.science/api/pith-number/POAHB5QZXIWSQ6NHIP3SV4YXR4/graph.json","fetch_events":"https://pith.science/api/pith-number/POAHB5QZXIWSQ6NHIP3SV4YXR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POAHB5QZXIWSQ6NHIP3SV4YXR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POAHB5QZXIWSQ6NHIP3SV4YXR4/action/storage_attestation","attest_author":"https://pith.science/pith/POAHB5QZXIWSQ6NHIP3SV4YXR4/action/author_attestation","sign_citation":"https://pith.science/pith/POAHB5QZXIWSQ6NHIP3SV4YXR4/action/citation_signature","submit_replication":"https://pith.science/pith/POAHB5QZXIWSQ6NHIP3SV4YXR4/action/replication_record"}},"created_at":"2026-07-05T01:54:46.736077+00:00","updated_at":"2026-07-05T01:54:46.736077+00:00"}