{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AQT3QA4ASABP73EISBCMKLHBNS","short_pith_number":"pith:AQT3QA4A","schema_version":"1.0","canonical_sha256":"0427b803809002ffec889044c52ce16c9ce8367104ae4b44a15ca91d086d1504","source":{"kind":"arxiv","id":"2411.19278","version":2},"attestation_state":"computed","paper":{"title":"OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Deng, Willow Yang, Yiming Zuo, Zeyu Ma","submitted_at":"2024-11-28T17:20:04Z","abstract_excerpt":"Depth completion (DC) aims to predict a dense depth map from an RGB image and a sparse depth map. Existing DC methods generalize poorly to new datasets or unseen sparse depth patterns, limiting their real-world applications. We propose OMNI-DC, a highly robust DC model that generalizes well zero-shot to various datasets. The key design is a novel Multi-resolution Depth Integrator, allowing our model to deal with very sparse depth inputs. We also introduce a novel Laplacian loss to model the ambiguity in the training process. Moreover, we train OMNI-DC on a mixture of high-quality datasets with"},"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":"2411.19278","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T17:20:04Z","cross_cats_sorted":[],"title_canon_sha256":"a9a236cddc0e52e3d3278cff7d5b37e9374016225740157153d9cb681a776e7a","abstract_canon_sha256":"a983e0204a814a15db101a4fe403465b6fbd5b9a3fcaa9b871394e10088c3d6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:52.439219Z","signature_b64":"vMXJuasR5V4PvLAfbxVRvgFrgIaOYCgYIqx4Kkb/xzOrQuGPSOyl/Lt9CAtcio2LyshdxqRX59WkCZ4EN0gyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0427b803809002ffec889044c52ce16c9ce8367104ae4b44a15ca91d086d1504","last_reissued_at":"2026-07-05T11:29:52.438752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:52.438752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Deng, Willow Yang, Yiming Zuo, Zeyu Ma","submitted_at":"2024-11-28T17:20:04Z","abstract_excerpt":"Depth completion (DC) aims to predict a dense depth map from an RGB image and a sparse depth map. Existing DC methods generalize poorly to new datasets or unseen sparse depth patterns, limiting their real-world applications. We propose OMNI-DC, a highly robust DC model that generalizes well zero-shot to various datasets. The key design is a novel Multi-resolution Depth Integrator, allowing our model to deal with very sparse depth inputs. We also introduce a novel Laplacian loss to model the ambiguity in the training process. Moreover, we train OMNI-DC on a mixture of high-quality datasets with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19278","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/2411.19278/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":"2411.19278","created_at":"2026-07-05T11:29:52.438810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19278v2","created_at":"2026-07-05T11:29:52.438810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19278","created_at":"2026-07-05T11:29:52.438810+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQT3QA4ASABP","created_at":"2026-07-05T11:29:52.438810+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQT3QA4ASABP73EI","created_at":"2026-07-05T11:29:52.438810+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQT3QA4A","created_at":"2026-07-05T11:29:52.438810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30115","citing_title":"Large Depth Completion Model from Sparse Observations","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS","json":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS.json","graph_json":"https://pith.science/api/pith-number/AQT3QA4ASABP73EISBCMKLHBNS/graph.json","events_json":"https://pith.science/api/pith-number/AQT3QA4ASABP73EISBCMKLHBNS/events.json","paper":"https://pith.science/paper/AQT3QA4A"},"agent_actions":{"view_html":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS","download_json":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS.json","view_paper":"https://pith.science/paper/AQT3QA4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19278&json=true","fetch_graph":"https://pith.science/api/pith-number/AQT3QA4ASABP73EISBCMKLHBNS/graph.json","fetch_events":"https://pith.science/api/pith-number/AQT3QA4ASABP73EISBCMKLHBNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS/action/storage_attestation","attest_author":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS/action/author_attestation","sign_citation":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS/action/citation_signature","submit_replication":"https://pith.science/pith/AQT3QA4ASABP73EISBCMKLHBNS/action/replication_record"}},"created_at":"2026-07-05T11:29:52.438810+00:00","updated_at":"2026-07-05T11:29:52.438810+00:00"}