{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XQEYLUXJJ6Y5QXMG63ZRFUBUYB","short_pith_number":"pith:XQEYLUXJ","schema_version":"1.0","canonical_sha256":"bc0985d2e94fb1d85d86f6f312d034c05e5b0040df988c5be6c1e780a88f3ad6","source":{"kind":"arxiv","id":"2212.00490","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Jiwen Yu, Yinhuai Wang","submitted_at":"2022-12-01T13:33:47Z","abstract_excerpt":"Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators. In this work, we propose the Denoising Diffusion Null-Space Model (DDNM), a novel zero-shot framework for arbitrary linear IR problems, including but not limited to image super-resolution, colorization, inpainting, compressed sensing, and deblurring. DDNM only needs a pre-trained off-the-shelf diffusion model as the generative prior, without any extra training or network modifications. By refining only the null-space contents during the reverse diffusion process, we c"},"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":"2212.00490","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T13:33:47Z","cross_cats_sorted":[],"title_canon_sha256":"ec34dbea001d732b67b20f59f6cd0e55680cfea771517f154f1acb2f90a86206","abstract_canon_sha256":"a0cabb5d3cc998e617c7c8a2e2a432366a6e2da14c6d0980167cb8bcbf579f73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:13.501366Z","signature_b64":"jTCdndv5WJN/aNJp3y5heSsrXpiEgskJbOSoCx5LlOIwOi7LHuNSqgwGJn4RMDGaWQ/wvS5hOcQhE2GwzCNoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc0985d2e94fb1d85d86f6f312d034c05e5b0040df988c5be6c1e780a88f3ad6","last_reissued_at":"2026-07-05T05:23:13.500949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:13.500949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Zhang, Jiwen Yu, Yinhuai Wang","submitted_at":"2022-12-01T13:33:47Z","abstract_excerpt":"Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators. In this work, we propose the Denoising Diffusion Null-Space Model (DDNM), a novel zero-shot framework for arbitrary linear IR problems, including but not limited to image super-resolution, colorization, inpainting, compressed sensing, and deblurring. DDNM only needs a pre-trained off-the-shelf diffusion model as the generative prior, without any extra training or network modifications. By refining only the null-space contents during the reverse diffusion process, we c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00490","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/2212.00490/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":"2212.00490","created_at":"2026-07-05T05:23:13.501006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.00490v2","created_at":"2026-07-05T05:23:13.501006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00490","created_at":"2026-07-05T05:23:13.501006+00:00"},{"alias_kind":"pith_short_12","alias_value":"XQEYLUXJJ6Y5","created_at":"2026-07-05T05:23:13.501006+00:00"},{"alias_kind":"pith_short_16","alias_value":"XQEYLUXJJ6Y5QXMG","created_at":"2026-07-05T05:23:13.501006+00:00"},{"alias_kind":"pith_short_8","alias_value":"XQEYLUXJ","created_at":"2026-07-05T05:23:13.501006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20763","citing_title":"From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20404","citing_title":"FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19195","citing_title":"Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04107","citing_title":"Reflection Separation from a Single Image via Joint Latent Diffusion","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02309","citing_title":"Measurement Geometry and Design for Trustworthy Generative Inverse Problems","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15050","citing_title":"Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18361","citing_title":"COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2602.07715","citing_title":"Analyzing and Guiding Zero-Shot Posterior Sampling in Diffusion Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04883","citing_title":"Protein Autoregressive Modeling via Multiscale Structure Generation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17353","citing_title":"Dual Ascent Diffusion for Inverse Problems","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16344","citing_title":"Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01608","citing_title":"NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2410.00083","citing_title":"A Survey on Diffusion Models for Inverse Problems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13278","citing_title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10275","citing_title":"PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05960","citing_title":"Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05387","citing_title":"Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01568","citing_title":"Unifying Deep Stochastic Processes for Image Enhancement","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11255","citing_title":"Invertible Diffusion for Low-Memory Channel Gain Map Construction in Wireless Communication Networks","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08922","citing_title":"Degradation-Robust Fusion: An Efficient Degradation-Aware Diffusion Framework for Multimodal Image Fusion in Arbitrary Degradation Scenarios","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06905","citing_title":"Conservative Flows: A New Paradigm of Generative Models","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB","json":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB.json","graph_json":"https://pith.science/api/pith-number/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/graph.json","events_json":"https://pith.science/api/pith-number/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/events.json","paper":"https://pith.science/paper/XQEYLUXJ"},"agent_actions":{"view_html":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB","download_json":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB.json","view_paper":"https://pith.science/paper/XQEYLUXJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.00490&json=true","fetch_graph":"https://pith.science/api/pith-number/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/graph.json","fetch_events":"https://pith.science/api/pith-number/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/action/storage_attestation","attest_author":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/action/author_attestation","sign_citation":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/action/citation_signature","submit_replication":"https://pith.science/pith/XQEYLUXJJ6Y5QXMG63ZRFUBUYB/action/replication_record"}},"created_at":"2026-07-05T05:23:13.501006+00:00","updated_at":"2026-07-05T05:23:13.501006+00:00"}