{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TIGRVVBH6LQ3QBM6G5MRQZVTCS","short_pith_number":"pith:TIGRVVBH","schema_version":"1.0","canonical_sha256":"9a0d1ad427f2e1b8059e37591866b31489954cb8da52dcecc4a26ac1e5a1fdfd","source":{"kind":"arxiv","id":"2505.17358","version":1},"attestation_state":"computed","paper":{"title":"Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chinmay Talegaonkar, Nicholas Antipa, Nikhil Gandudi Suresh, Priyanka Nagasamudra, Yash Belhe, Zachary Novack","submitted_at":"2025-05-23T00:27:23Z","abstract_excerpt":"Recent monocular metric depth estimation (MMDE) methods have made notable progress towards zero-shot generalization. However, they still exhibit a significant performance drop on out-of-distribution datasets. We address this limitation by injecting defocus blur cues at inference time into Marigold, a \\textit{pre-trained} diffusion model for zero-shot, scale-invariant monocular depth estimation (MDE). Our method effectively turns Marigold into a metric depth predictor in a training-free manner. To incorporate defocus cues, we capture two images with a small and a large aperture from the same vi"},"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":"2505.17358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T00:27:23Z","cross_cats_sorted":[],"title_canon_sha256":"1f794ec8ccf2bf99293888b221971475f7fbbaac2106cf3bfb53317ba4c050bb","abstract_canon_sha256":"352ddba3665206e25163c747154088ebb0a38014e947e1b5bdcac3653ca5d749"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:24.627095Z","signature_b64":"4MLYBSgemTFAl7fTEG3Ezd1wQDEYhQTocIDHMPExnp6m0WK62ixhbcbP/ndi7t5pk2iMM4yl8WgJRcb2DDOyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a0d1ad427f2e1b8059e37591866b31489954cb8da52dcecc4a26ac1e5a1fdfd","last_reissued_at":"2026-07-05T11:08:24.626616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:24.626616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chinmay Talegaonkar, Nicholas Antipa, Nikhil Gandudi Suresh, Priyanka Nagasamudra, Yash Belhe, Zachary Novack","submitted_at":"2025-05-23T00:27:23Z","abstract_excerpt":"Recent monocular metric depth estimation (MMDE) methods have made notable progress towards zero-shot generalization. However, they still exhibit a significant performance drop on out-of-distribution datasets. We address this limitation by injecting defocus blur cues at inference time into Marigold, a \\textit{pre-trained} diffusion model for zero-shot, scale-invariant monocular depth estimation (MDE). Our method effectively turns Marigold into a metric depth predictor in a training-free manner. To incorporate defocus cues, we capture two images with a small and a large aperture from the same vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17358","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/2505.17358/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":"2505.17358","created_at":"2026-07-05T11:08:24.626672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17358v1","created_at":"2026-07-05T11:08:24.626672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17358","created_at":"2026-07-05T11:08:24.626672+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIGRVVBH6LQ3","created_at":"2026-07-05T11:08:24.626672+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIGRVVBH6LQ3QBM6","created_at":"2026-07-05T11:08:24.626672+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIGRVVBH","created_at":"2026-07-05T11:08:24.626672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS","json":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS.json","graph_json":"https://pith.science/api/pith-number/TIGRVVBH6LQ3QBM6G5MRQZVTCS/graph.json","events_json":"https://pith.science/api/pith-number/TIGRVVBH6LQ3QBM6G5MRQZVTCS/events.json","paper":"https://pith.science/paper/TIGRVVBH"},"agent_actions":{"view_html":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS","download_json":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS.json","view_paper":"https://pith.science/paper/TIGRVVBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17358&json=true","fetch_graph":"https://pith.science/api/pith-number/TIGRVVBH6LQ3QBM6G5MRQZVTCS/graph.json","fetch_events":"https://pith.science/api/pith-number/TIGRVVBH6LQ3QBM6G5MRQZVTCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS/action/storage_attestation","attest_author":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS/action/author_attestation","sign_citation":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS/action/citation_signature","submit_replication":"https://pith.science/pith/TIGRVVBH6LQ3QBM6G5MRQZVTCS/action/replication_record"}},"created_at":"2026-07-05T11:08:24.626672+00:00","updated_at":"2026-07-05T11:08:24.626672+00:00"}