{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MCPW6WWHUR6HZEE2PBEANYGWNI","short_pith_number":"pith:MCPW6WWH","schema_version":"1.0","canonical_sha256":"609f6f5ac7a47c7c909a784806e0d66a26aa91634b13db8e9d888c7e66bb8979","source":{"kind":"arxiv","id":"2406.11711","version":1},"attestation_state":"computed","paper":{"title":"OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Deng, Yiming Zuo","submitted_at":"2024-06-17T16:30:29Z","abstract_excerpt":"Depth completion is the task of generating a dense depth map given an image and a sparse depth map as inputs. It has important applications in various downstream tasks. In this paper, we present OGNI-DC, a novel framework for depth completion. The key to our method is \"Optimization-Guided Neural Iterations\" (OGNI). It consists of a recurrent unit that refines a depth gradient field and a differentiable depth integrator that integrates the depth gradients into a depth map. OGNI-DC exhibits strong generalization, outperforming baselines by a large margin on unseen datasets and across various spa"},"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":"2406.11711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T16:30:29Z","cross_cats_sorted":[],"title_canon_sha256":"57e999aac3f6fe383425a2b55c3671bef41e9974090eea5f992cba1b46b54736","abstract_canon_sha256":"883e1bb1e3600f6b6711fa95031532215667ac1a859ee03374cfcc62694aea97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:56.749219Z","signature_b64":"c04h1Z+v08uLNFzcy1YpjgqZq0A+xtA+A21UORQ+8fpRxQ+x5qiynpVZEkpYM4gGaOqJdQUm68yA/W6ZqyizDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"609f6f5ac7a47c7c909a784806e0d66a26aa91634b13db8e9d888c7e66bb8979","last_reissued_at":"2026-07-05T08:32:56.748741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:56.748741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jia Deng, Yiming Zuo","submitted_at":"2024-06-17T16:30:29Z","abstract_excerpt":"Depth completion is the task of generating a dense depth map given an image and a sparse depth map as inputs. It has important applications in various downstream tasks. In this paper, we present OGNI-DC, a novel framework for depth completion. The key to our method is \"Optimization-Guided Neural Iterations\" (OGNI). It consists of a recurrent unit that refines a depth gradient field and a differentiable depth integrator that integrates the depth gradients into a depth map. OGNI-DC exhibits strong generalization, outperforming baselines by a large margin on unseen datasets and across various spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11711","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/2406.11711/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":"2406.11711","created_at":"2026-07-05T08:32:56.748799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11711v1","created_at":"2026-07-05T08:32:56.748799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11711","created_at":"2026-07-05T08:32:56.748799+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCPW6WWHUR6H","created_at":"2026-07-05T08:32:56.748799+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCPW6WWHUR6HZEE2","created_at":"2026-07-05T08:32:56.748799+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCPW6WWH","created_at":"2026-07-05T08:32:56.748799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16545","citing_title":"ToF-Splatting: Dense SLAM using Sparse Time-of-Flight Depth and Multi-Frame Integration","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI","json":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI.json","graph_json":"https://pith.science/api/pith-number/MCPW6WWHUR6HZEE2PBEANYGWNI/graph.json","events_json":"https://pith.science/api/pith-number/MCPW6WWHUR6HZEE2PBEANYGWNI/events.json","paper":"https://pith.science/paper/MCPW6WWH"},"agent_actions":{"view_html":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI","download_json":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI.json","view_paper":"https://pith.science/paper/MCPW6WWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11711&json=true","fetch_graph":"https://pith.science/api/pith-number/MCPW6WWHUR6HZEE2PBEANYGWNI/graph.json","fetch_events":"https://pith.science/api/pith-number/MCPW6WWHUR6HZEE2PBEANYGWNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI/action/storage_attestation","attest_author":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI/action/author_attestation","sign_citation":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI/action/citation_signature","submit_replication":"https://pith.science/pith/MCPW6WWHUR6HZEE2PBEANYGWNI/action/replication_record"}},"created_at":"2026-07-05T08:32:56.748799+00:00","updated_at":"2026-07-05T08:32:56.748799+00:00"}