{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GNLUADVJQA52JZCG4FTTCSYW4K","short_pith_number":"pith:GNLUADVJ","schema_version":"1.0","canonical_sha256":"3357400ea9803ba4e446e167314b16e29555d388e8ed181446ab50656ae8d3ae","source":{"kind":"arxiv","id":"2405.19657","version":1},"attestation_state":"computed","paper":{"title":"Uncertainty-guided Optimal Transport in Depth Supervised Sparse-View 3D Gaussian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianbin Jiao, Qixiang Ye, Qi Zhang, Wei Sun, Yanzhao Zhou, Yuan Li","submitted_at":"2024-05-30T03:18:30Z","abstract_excerpt":"3D Gaussian splatting has demonstrated impressive performance in real-time novel view synthesis. However, achieving successful reconstruction from RGB images generally requires multiple input views captured under static conditions. To address the challenge of sparse input views, previous approaches have incorporated depth supervision into the training of 3D Gaussians to mitigate overfitting, using dense predictions from pretrained depth networks as pseudo-ground truth. Nevertheless, depth predictions from monocular depth estimation models inherently exhibit significant uncertainty in specific "},"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":"2405.19657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T03:18:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"81130c53c0d0da97577a5bfc6ddc76a5a20f3287d4922dc0284251aeee243710","abstract_canon_sha256":"2b2a6797c16e1998b8e2be9f18d17303119b49fb9ecb12d0b84d29fee0bebdf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:10.795067Z","signature_b64":"g7VeihOp2N0BKjR817D9GhFvfb51vbH/Xf+Ygb0nIfER6n/NTRqeXtLcIar2Bb4kQwGruUE34jLKGh6mdSpdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3357400ea9803ba4e446e167314b16e29555d388e8ed181446ab50656ae8d3ae","last_reissued_at":"2026-07-05T08:25:10.794597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:10.794597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-guided Optimal Transport in Depth Supervised Sparse-View 3D Gaussian","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianbin Jiao, Qixiang Ye, Qi Zhang, Wei Sun, Yanzhao Zhou, Yuan Li","submitted_at":"2024-05-30T03:18:30Z","abstract_excerpt":"3D Gaussian splatting has demonstrated impressive performance in real-time novel view synthesis. However, achieving successful reconstruction from RGB images generally requires multiple input views captured under static conditions. To address the challenge of sparse input views, previous approaches have incorporated depth supervision into the training of 3D Gaussians to mitigate overfitting, using dense predictions from pretrained depth networks as pseudo-ground truth. Nevertheless, depth predictions from monocular depth estimation models inherently exhibit significant uncertainty in specific "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19657","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/2405.19657/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":"2405.19657","created_at":"2026-07-05T08:25:10.794652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19657v1","created_at":"2026-07-05T08:25:10.794652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19657","created_at":"2026-07-05T08:25:10.794652+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNLUADVJQA52","created_at":"2026-07-05T08:25:10.794652+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNLUADVJQA52JZCG","created_at":"2026-07-05T08:25:10.794652+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNLUADVJ","created_at":"2026-07-05T08:25:10.794652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.15355","citing_title":"DAV-GSWT: Diffusion-Active-View Sampling for Data-Efficient Gaussian Splatting Wang Tiles","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K","json":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K.json","graph_json":"https://pith.science/api/pith-number/GNLUADVJQA52JZCG4FTTCSYW4K/graph.json","events_json":"https://pith.science/api/pith-number/GNLUADVJQA52JZCG4FTTCSYW4K/events.json","paper":"https://pith.science/paper/GNLUADVJ"},"agent_actions":{"view_html":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K","download_json":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K.json","view_paper":"https://pith.science/paper/GNLUADVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19657&json=true","fetch_graph":"https://pith.science/api/pith-number/GNLUADVJQA52JZCG4FTTCSYW4K/graph.json","fetch_events":"https://pith.science/api/pith-number/GNLUADVJQA52JZCG4FTTCSYW4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K/action/storage_attestation","attest_author":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K/action/author_attestation","sign_citation":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K/action/citation_signature","submit_replication":"https://pith.science/pith/GNLUADVJQA52JZCG4FTTCSYW4K/action/replication_record"}},"created_at":"2026-07-05T08:25:10.794652+00:00","updated_at":"2026-07-05T08:25:10.794652+00:00"}