{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HFROCVKFR57YYFW53RFIPJSTF7","short_pith_number":"pith:HFROCVKF","schema_version":"1.0","canonical_sha256":"3962e155458f7f8c16dddc4a87a6532fda72a296c39b12ff7ee03ddf38325ba3","source":{"kind":"arxiv","id":"2412.13389","version":2},"attestation_state":"computed","paper":{"title":"Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Becker, Anton Obukhov, Bingxin Ke, Kevin Qu, Konrad Schindler, Massimiliano Viola, Nando Metzger","submitted_at":"2024-12-18T00:06:41Z","abstract_excerpt":"Depth completion upgrades sparse depth measurements into dense depth maps guided by a conventional image. Existing methods for this highly ill-posed task operate in tightly constrained settings and tend to struggle when applied to images outside the training domain or when the available depth measurements are sparse, irregularly distributed, or of varying density. Inspired by recent advances in monocular depth estimation, we reframe depth completion as an image-conditional depth map generation guided by sparse measurements. Our method, Marigold-DC, builds on a pretrained latent diffusion model"},"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":"2412.13389","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T00:06:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d85faa0491cc3ceefd1da5827c27a4372c6ffe81ff7e302dbd49d550d506eed0","abstract_canon_sha256":"b7580cc3dc65991d9ea51c2600f06270d2a58b149d5afd5a9ad65b68ecb71f22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:14.743134Z","signature_b64":"AOazw6vikhECTUuuZtDLLd7a1/aMtpuuImhqZnaYeqpC2ttROdCNoD2yGs8QbfeJlMjmz187+yJx+mRums6tAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3962e155458f7f8c16dddc4a87a6532fda72a296c39b12ff7ee03ddf38325ba3","last_reissued_at":"2026-07-05T12:11:14.742594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:14.742594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Becker, Anton Obukhov, Bingxin Ke, Kevin Qu, Konrad Schindler, Massimiliano Viola, Nando Metzger","submitted_at":"2024-12-18T00:06:41Z","abstract_excerpt":"Depth completion upgrades sparse depth measurements into dense depth maps guided by a conventional image. Existing methods for this highly ill-posed task operate in tightly constrained settings and tend to struggle when applied to images outside the training domain or when the available depth measurements are sparse, irregularly distributed, or of varying density. Inspired by recent advances in monocular depth estimation, we reframe depth completion as an image-conditional depth map generation guided by sparse measurements. Our method, Marigold-DC, builds on a pretrained latent diffusion model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13389","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/2412.13389/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":"2412.13389","created_at":"2026-07-05T12:11:14.742664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13389v2","created_at":"2026-07-05T12:11:14.742664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13389","created_at":"2026-07-05T12:11:14.742664+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFROCVKFR57Y","created_at":"2026-07-05T12:11:14.742664+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFROCVKFR57YYFW5","created_at":"2026-07-05T12:11:14.742664+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFROCVKF","created_at":"2026-07-05T12:11:14.742664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24301","citing_title":"MM-TRELLIS: Point-Cloud Guided Multi-Modal 3D Vehicle Generation in Autonomous Driving","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12608","citing_title":"A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30115","citing_title":"Large Depth Completion Model from Sparse Observations","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17182","citing_title":"Radar-Guided Polynomial Fitting for Metric Depth Estimation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12608","citing_title":"A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7","json":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7.json","graph_json":"https://pith.science/api/pith-number/HFROCVKFR57YYFW53RFIPJSTF7/graph.json","events_json":"https://pith.science/api/pith-number/HFROCVKFR57YYFW53RFIPJSTF7/events.json","paper":"https://pith.science/paper/HFROCVKF"},"agent_actions":{"view_html":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7","download_json":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7.json","view_paper":"https://pith.science/paper/HFROCVKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13389&json=true","fetch_graph":"https://pith.science/api/pith-number/HFROCVKFR57YYFW53RFIPJSTF7/graph.json","fetch_events":"https://pith.science/api/pith-number/HFROCVKFR57YYFW53RFIPJSTF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7/action/storage_attestation","attest_author":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7/action/author_attestation","sign_citation":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7/action/citation_signature","submit_replication":"https://pith.science/pith/HFROCVKFR57YYFW53RFIPJSTF7/action/replication_record"}},"created_at":"2026-07-05T12:11:14.742664+00:00","updated_at":"2026-07-05T12:11:14.742664+00:00"}