{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-samplers-for-inverse-problems-in","title":"Fast Samplers for Inverse Problems in Iterative Refinement Models","arxiv_id":"2405.17673","date":"2024-05-27","proceeding":null,"authors":["Kushagra Pandey","Ruihan Yang","Stephan Mandt"],"abstract":"Constructing fast samplers for unconditional diffusion and flow-matching models has received much attention recently; however, existing methods for solving inverse problems, such as super-resolution, inpainting, or deblurring, still require hundreds to thousands of iterative steps to obtain high-quality results. We propose a plug-and-play framework for constructing efficient samplers for inverse problems, requiring only pre-trained diffusion or flow-matching models. We present Conditional Conjugate Integrators, which leverage the specific form of the inverse problem to project the respective conditional diffusion/flow dynamics into a more amenable space for sampling. Our method complements popular posterior approximation methods for solving inverse problems using diffusion/flow models. We evaluate the proposed method's performance on various linear image restoration tasks across multiple datasets, employing diffusion and flow-matching models. Notably, on challenging inverse problems like 4x super-resolution on the ImageNet dataset, our method can generate high-quality samples in as few as 5 conditional sampling steps and outperforms competing baselines requiring 20-1000 steps. Our code will be publicly available at https://github.com/mandt-lab/c-pigdm","url_abs":"https://arxiv.org/abs/2405.17673v2","url_pdf":"https://arxiv.org/pdf/2405.17673v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-samplers-for-inverse-problems-in","repo_url":"https://github.com/mandt-lab/c-pigdm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"fast-samplers-for-inverse-problems-in","repo_url":"https://github.com/mandt-lab/ci2rm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deblurring","task_name":"Deblurring"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.17673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17673"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/mandt-lab/c-pigdm","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/NVlabs/RED-diff","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/gnobitab/RectifiedFlow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mandt-lab/ci2rm","reach":null}],"summary":{"ran":4,"ran_draft_wrong":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":2},"found_in_text":{"samples":4,"ran":3,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":8,"samples":[{"code_sha256_prefix":"401b0f6645e0528f","entry":"Conjugate","repo":"mandt-lab/ci2rm","repo_kind":"official","path":"flow/sampler.py","file_url":"https://github.com/mandt-lab/ci2rm/blob/HEAD/flow/sampler.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"401b0f6645e0528f"}},{"code_sha256_prefix":"d96f46caebdb91c0","entry":"center_crop_arr","repo":"NVlabs/RED-diff","repo_kind":"found_in_text","path":"datasets/imagenet.py","file_url":"https://github.com/NVlabs/RED-diff/blob/HEAD/datasets/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d96f46caebdb91c0"}},{"code_sha256_prefix":"84f1005930b04eee","entry":"from_flattened_numpy","repo":"gnobitab/RectifiedFlow","repo_kind":"found_in_text","path":"ImageGeneration/sampling.py","file_url":"https://github.com/gnobitab/RectifiedFlow/blob/HEAD/ImageGeneration/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"84f1005930b04eee"}},{"code_sha256_prefix":"8ff7c24dade9904c","entry":"get_optimizer","repo":"mandt-lab/c-pigdm","repo_kind":"official","path":"flow/losses.py","file_url":"https://github.com/mandt-lab/c-pigdm/blob/HEAD/flow/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ff7c24dade9904c"}},{"code_sha256_prefix":"4b3dc148a2e2a2e6","entry":"get_rectified_flow_sampler","repo":"gnobitab/RectifiedFlow","repo_kind":"found_in_text","path":"ImageGeneration/sampling.py","file_url":"https://github.com/gnobitab/RectifiedFlow/blob/HEAD/ImageGeneration/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b3dc148a2e2a2e6"}},{"code_sha256_prefix":"366bb8c7035a2fc8","entry":"optimization_manager","repo":"mandt-lab/c-pigdm","repo_kind":"official","path":"flow/losses.py","file_url":"https://github.com/mandt-lab/c-pigdm/blob/HEAD/flow/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"366bb8c7035a2fc8"}},{"code_sha256_prefix":"d0bdb81d2cb8c3e7","entry":"to_flattened_numpy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"d0bdb81d2cb8c3e7"}},{"code_sha256_prefix":"6e6c81454ec88afd","entry":"get_imagenet_loader","repo":"NVlabs/RED-diff","repo_kind":"found_in_text","path":"datasets/imagenet.py","file_url":"https://github.com/NVlabs/RED-diff/blob/HEAD/datasets/imagenet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6e6c81454ec88afd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}