{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XQFBSHKZBYKPFCP56LPXSEDJLL","short_pith_number":"pith:XQFBSHKZ","schema_version":"1.0","canonical_sha256":"bc0a191d590e14f289fdf2df7910695af091f9d7834f411013af33830f1997a8","source":{"kind":"arxiv","id":"2403.13788","version":2},"attestation_state":"computed","paper":{"title":"DepthFM: Fast Monocular Depth Estimation with Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Dmytro Kotovenko, Johannes Schusterbauer, Ming Gui, Olga Grebenkova, Pingchuan Ma, Stefan Andreas Baumann, Ulrich Prestel, Vincent Tao Hu","submitted_at":"2024-03-20T17:51:53Z","abstract_excerpt":"Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth estimation as a direct transport between image and depth distributions. We are the first to explore flow matching in this field, and we demonstrate that its interpolation trajectories enhance both training and sampling efficiency while preserving high performance. While generative models typically require extensive training data, we mitigate this dependency "},"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":"2403.13788","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T17:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"d6bd2e045c31ed36b2af18578408f88f2b72aa383b22325dece03d80e4d6cbc9","abstract_canon_sha256":"35a29eddad241faef8e66deb77645b58a6ac28ae0183daff38997bac866261dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:31.634417Z","signature_b64":"et3g2I1FevDJeCwJSXhG168uxTEGWOH4IQuaa8UXty96Xc+GFPbfFL5K6fOWRppbSzy80ThU3KV6XIvlj+QSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc0a191d590e14f289fdf2df7910695af091f9d7834f411013af33830f1997a8","last_reissued_at":"2026-07-05T09:51:31.633847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:31.633847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DepthFM: Fast Monocular Depth Estimation with Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Ommer, Dmytro Kotovenko, Johannes Schusterbauer, Ming Gui, Olga Grebenkova, Pingchuan Ma, Stefan Andreas Baumann, Ulrich Prestel, Vincent Tao Hu","submitted_at":"2024-03-20T17:51:53Z","abstract_excerpt":"Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth estimation as a direct transport between image and depth distributions. We are the first to explore flow matching in this field, and we demonstrate that its interpolation trajectories enhance both training and sampling efficiency while preserving high performance. While generative models typically require extensive training data, we mitigate this dependency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13788","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/2403.13788/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":"2403.13788","created_at":"2026-07-05T09:51:31.633927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13788v2","created_at":"2026-07-05T09:51:31.633927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13788","created_at":"2026-07-05T09:51:31.633927+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQFBSHKZBYKP","created_at":"2026-07-05T09:51:31.633927+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQFBSHKZBYKPFCP5","created_at":"2026-07-05T09:51:31.633927+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQFBSHKZ","created_at":"2026-07-05T09:51:31.633927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24874","citing_title":"FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21300","citing_title":"SCOPE: Scale-Consistent One-Pass Estimation of 3D Geometry","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17030","citing_title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","ref_index":296,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30332","citing_title":"UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2508.14461","citing_title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02546","citing_title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09414","citing_title":"Depth Anything V2","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00658","citing_title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2508.02324","citing_title":"Qwen-Image Technical Report","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL","json":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL.json","graph_json":"https://pith.science/api/pith-number/XQFBSHKZBYKPFCP56LPXSEDJLL/graph.json","events_json":"https://pith.science/api/pith-number/XQFBSHKZBYKPFCP56LPXSEDJLL/events.json","paper":"https://pith.science/paper/XQFBSHKZ"},"agent_actions":{"view_html":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL","download_json":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL.json","view_paper":"https://pith.science/paper/XQFBSHKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13788&json=true","fetch_graph":"https://pith.science/api/pith-number/XQFBSHKZBYKPFCP56LPXSEDJLL/graph.json","fetch_events":"https://pith.science/api/pith-number/XQFBSHKZBYKPFCP56LPXSEDJLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL/action/storage_attestation","attest_author":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL/action/author_attestation","sign_citation":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL/action/citation_signature","submit_replication":"https://pith.science/pith/XQFBSHKZBYKPFCP56LPXSEDJLL/action/replication_record"}},"created_at":"2026-07-05T09:51:31.633927+00:00","updated_at":"2026-07-05T09:51:31.633927+00:00"}