{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZD3C52JAKHWMU7PQQW6YWM2CU7","short_pith_number":"pith:ZD3C52JA","schema_version":"1.0","canonical_sha256":"c8f62ee92051ecca7df085bd8b3342a7ec40594d0f86a83b7ba3b753dd514e89","source":{"kind":"arxiv","id":"1907.10326","version":6},"attestation_state":"computed","paper":{"title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Wook Ko, Il hong Suh, Jin Han Lee, Myung-Kyu Han","submitted_at":"2019-07-24T09:31:24Z","abstract_excerpt":"Estimating accurate depth from a single image is challenging because it is an ill-posed problem as infinitely many 3D scenes can be projected to the same 2D scene. However, recent works based on deep convolutional neural networks show great progress with plausible results. The convolutional neural networks are generally composed of two parts: an encoder for dense feature extraction and a decoder for predicting the desired depth. In the encoder-decoder schemes, repeated strided convolution and spatial pooling layers lower the spatial resolution of transitional outputs, and several techniques su"},"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":"1907.10326","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-24T09:31:24Z","cross_cats_sorted":[],"title_canon_sha256":"05d48f2abbcc190f0df0527a46bf57214ad21fab07e15f9e97f22d7a4d7d4dca","abstract_canon_sha256":"601118501b6bc7705646911c741e31fe37b6925beafd65301464f2156096c908"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:16:48.657039Z","signature_b64":"flBsdJrg0r1yXcPwoiDRe+kW+Z3DNVKB3ACjygZsMUA8HQAJ1GzBZAWFqErunf2vVeB3AHEGLNu/sSM37E0IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8f62ee92051ecca7df085bd8b3342a7ec40594d0f86a83b7ba3b753dd514e89","last_reissued_at":"2026-07-05T03:16:48.656500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:16:48.656500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Wook Ko, Il hong Suh, Jin Han Lee, Myung-Kyu Han","submitted_at":"2019-07-24T09:31:24Z","abstract_excerpt":"Estimating accurate depth from a single image is challenging because it is an ill-posed problem as infinitely many 3D scenes can be projected to the same 2D scene. However, recent works based on deep convolutional neural networks show great progress with plausible results. The convolutional neural networks are generally composed of two parts: an encoder for dense feature extraction and a decoder for predicting the desired depth. In the encoder-decoder schemes, repeated strided convolution and spatial pooling layers lower the spatial resolution of transitional outputs, and several techniques su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10326","kind":"arxiv","version":6},"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/1907.10326/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":"1907.10326","created_at":"2026-07-05T03:16:48.656564+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.10326v6","created_at":"2026-07-05T03:16:48.656564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10326","created_at":"2026-07-05T03:16:48.656564+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZD3C52JAKHWM","created_at":"2026-07-05T03:16:48.656564+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZD3C52JAKHWMU7PQ","created_at":"2026-07-05T03:16:48.656564+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZD3C52JA","created_at":"2026-07-05T03:16:48.656564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13289","citing_title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31488","citing_title":"DrivingDepth: Sparse-Prompted Pixel-wise Scale Correction for Driving Depth Estimation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28735","citing_title":"SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31466","citing_title":"VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17182","citing_title":"Radar-Guided Polynomial Fitting for Metric Depth Estimation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13977","citing_title":"ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2502.20110","citing_title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09532","citing_title":"RAD: Retrieval-Augmented Monocular Metric Depth Estimation for Underrepresented Classes","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01765","citing_title":"Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27105","citing_title":"UniDAC: Universal Metric Depth Estimation for Any Camera","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2302.12288","citing_title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03339","citing_title":"Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26454","citing_title":"Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10251","citing_title":"Efficient Hybrid CNN-GNN Architecture for Monocular Depth Estimation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06665","citing_title":"VDPP: Video Depth Post-Processing for Speed and Scalability","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06576","citing_title":"LiftFormer: Lifting and Frame Theory Based Monocular Depth Estimation Using Depth and Edge Oriented Subspace Representation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7","json":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7.json","graph_json":"https://pith.science/api/pith-number/ZD3C52JAKHWMU7PQQW6YWM2CU7/graph.json","events_json":"https://pith.science/api/pith-number/ZD3C52JAKHWMU7PQQW6YWM2CU7/events.json","paper":"https://pith.science/paper/ZD3C52JA"},"agent_actions":{"view_html":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7","download_json":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7.json","view_paper":"https://pith.science/paper/ZD3C52JA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.10326&json=true","fetch_graph":"https://pith.science/api/pith-number/ZD3C52JAKHWMU7PQQW6YWM2CU7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZD3C52JAKHWMU7PQQW6YWM2CU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7/action/storage_attestation","attest_author":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7/action/author_attestation","sign_citation":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7/action/citation_signature","submit_replication":"https://pith.science/pith/ZD3C52JAKHWMU7PQQW6YWM2CU7/action/replication_record"}},"created_at":"2026-07-05T03:16:48.656564+00:00","updated_at":"2026-07-05T03:16:48.656564+00:00"}