{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:4SAVOLXY6GLEOOPYWRRLEOMI3H","short_pith_number":"pith:4SAVOLXY","schema_version":"1.0","canonical_sha256":"e481572ef8f1964739f8b462b23988d9f3a0322afc07e02d30f86fd2cc6d78dd","source":{"kind":"arxiv","id":"1611.05705","version":4},"attestation_state":"computed","paper":{"title":"DSAC - Differentiable RANSAC for Camera Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Krull, Carsten Rother, Eric Brachmann, Frank Michel, Jamie Shotton, Sebastian Nowozin, Stefan Gumhold","submitted_at":"2016-11-17T14:39:53Z","abstract_excerpt":"RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far not been used as part of such deep learning pipelines, because its hypothesis selection procedure is non-differentiable. In this work, we present two different ways to overcome this limitation. The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypo"},"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":"1611.05705","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-17T14:39:53Z","cross_cats_sorted":[],"title_canon_sha256":"47fc830ce9ef9a4e410f6e1152ac3a41ef0c707aa11fe2e29cbb870da7f674e7","abstract_canon_sha256":"032017f9091479ab1370dc97b117372306da09a0c4b47435f48bc06085cf7041"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:32.460950Z","signature_b64":"F2EUfvg5iwOk6fNNJzfFSDTmHNYmak211SI5w5sV9d2pNWfv9eLJ8Y3ygplUCiCJXGqPf1mfUf657dKNK+otDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e481572ef8f1964739f8b462b23988d9f3a0322afc07e02d30f86fd2cc6d78dd","last_reissued_at":"2026-05-18T00:20:32.460370Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:32.460370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSAC - Differentiable RANSAC for Camera Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Krull, Carsten Rother, Eric Brachmann, Frank Michel, Jamie Shotton, Sebastian Nowozin, Stefan Gumhold","submitted_at":"2016-11-17T14:39:53Z","abstract_excerpt":"RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far not been used as part of such deep learning pipelines, because its hypothesis selection procedure is non-differentiable. In this work, we present two different ways to overcome this limitation. The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05705","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1611.05705","created_at":"2026-05-18T00:20:32.460453+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05705v4","created_at":"2026-05-18T00:20:32.460453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05705","created_at":"2026-05-18T00:20:32.460453+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SAVOLXY6GLE","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SAVOLXY6GLEOOPY","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SAVOLXY","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H","json":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H.json","graph_json":"https://pith.science/api/pith-number/4SAVOLXY6GLEOOPYWRRLEOMI3H/graph.json","events_json":"https://pith.science/api/pith-number/4SAVOLXY6GLEOOPYWRRLEOMI3H/events.json","paper":"https://pith.science/paper/4SAVOLXY"},"agent_actions":{"view_html":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H","download_json":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H.json","view_paper":"https://pith.science/paper/4SAVOLXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05705&json=true","fetch_graph":"https://pith.science/api/pith-number/4SAVOLXY6GLEOOPYWRRLEOMI3H/graph.json","fetch_events":"https://pith.science/api/pith-number/4SAVOLXY6GLEOOPYWRRLEOMI3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H/action/storage_attestation","attest_author":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H/action/author_attestation","sign_citation":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H/action/citation_signature","submit_replication":"https://pith.science/pith/4SAVOLXY6GLEOOPYWRRLEOMI3H/action/replication_record"}},"created_at":"2026-05-18T00:20:32.460453+00:00","updated_at":"2026-05-18T00:20:32.460453+00:00"}