{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I5B76VGUPA6XRQ76GCL5BJB5HT","short_pith_number":"pith:I5B76VGU","schema_version":"1.0","canonical_sha256":"4743ff54d4783d78c3fe3097d0a43d3cf5280907c6193690160b44c42652c883","source":{"kind":"arxiv","id":"2303.11435","version":5},"attestation_state":"computed","paper":{"title":"Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Mauricio Delbracio, Peyman Milanfar","submitted_at":"2023-03-20T20:28:17Z","abstract_excerpt":"Inversion by Direct Iteration (InDI) is a new formulation for supervised image restoration that avoids the so-called \"regression to the mean\" effect and produces more realistic and detailed images than existing regression-based methods. It does this by gradually improving image quality in small steps, similar to generative denoising diffusion models. Image restoration is an ill-posed problem where multiple high-quality images are plausible reconstructions of a given low-quality input. Therefore, the outcome of a single step regression model is typically an aggregate of all possible explanation"},"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":"2303.11435","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2023-03-20T20:28:17Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"a586934e4279e2fc7397bc1591721c0c56ffc3e09299d6fe6c85c58d4c5a3d4a","abstract_canon_sha256":"21d63f6c24724797cf207d4891193e9115c0f5ee762067e628787912f69eefc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:40.205222Z","signature_b64":"EIA9v31ps32bINMf0xHx94rF2s73hSMw4lkbjmxOb9zMbe9tLTOpd+1J9KqPXSsGQFbfF5ln4Q/y+o7sRLglCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4743ff54d4783d78c3fe3097d0a43d3cf5280907c6193690160b44c42652c883","last_reissued_at":"2026-07-05T07:40:40.204736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:40.204736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Mauricio Delbracio, Peyman Milanfar","submitted_at":"2023-03-20T20:28:17Z","abstract_excerpt":"Inversion by Direct Iteration (InDI) is a new formulation for supervised image restoration that avoids the so-called \"regression to the mean\" effect and produces more realistic and detailed images than existing regression-based methods. It does this by gradually improving image quality in small steps, similar to generative denoising diffusion models. Image restoration is an ill-posed problem where multiple high-quality images are plausible reconstructions of a given low-quality input. Therefore, the outcome of a single step regression model is typically an aggregate of all possible explanation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11435","kind":"arxiv","version":5},"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/2303.11435/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":"2303.11435","created_at":"2026-07-05T07:40:40.204794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11435v5","created_at":"2026-07-05T07:40:40.204794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11435","created_at":"2026-07-05T07:40:40.204794+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5B76VGUPA6X","created_at":"2026-07-05T07:40:40.204794+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5B76VGUPA6XRQ76","created_at":"2026-07-05T07:40:40.204794+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5B76VGU","created_at":"2026-07-05T07:40:40.204794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25014","citing_title":"Stop Denoising Your Blurs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2508.04832","citing_title":"Deep Distillation Gradient Preconditioning for Inverse Problems","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15456","citing_title":"DIPA: Distilled Preconditioned Algorithms for Solving Imaging Inverse Problems","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06024","citing_title":"On Inverse Problems, Parameter Estimation, and Domain Generalization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01568","citing_title":"Unifying Deep Stochastic Processes for Image Enhancement","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06568","citing_title":"A Noise Constrained Diffusion (NC-Diffusion) Framework for High Fidelity Image Compression","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16955","citing_title":"Training-inference input alignment outweighs framework choice in longitudinal retinal image prediction","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT","json":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT.json","graph_json":"https://pith.science/api/pith-number/I5B76VGUPA6XRQ76GCL5BJB5HT/graph.json","events_json":"https://pith.science/api/pith-number/I5B76VGUPA6XRQ76GCL5BJB5HT/events.json","paper":"https://pith.science/paper/I5B76VGU"},"agent_actions":{"view_html":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT","download_json":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT.json","view_paper":"https://pith.science/paper/I5B76VGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11435&json=true","fetch_graph":"https://pith.science/api/pith-number/I5B76VGUPA6XRQ76GCL5BJB5HT/graph.json","fetch_events":"https://pith.science/api/pith-number/I5B76VGUPA6XRQ76GCL5BJB5HT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT/action/storage_attestation","attest_author":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT/action/author_attestation","sign_citation":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT/action/citation_signature","submit_replication":"https://pith.science/pith/I5B76VGUPA6XRQ76GCL5BJB5HT/action/replication_record"}},"created_at":"2026-07-05T07:40:40.204794+00:00","updated_at":"2026-07-05T07:40:40.204794+00:00"}