{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/bayesian-image-reconstruction-using-deep","title":"Bayesian Image Reconstruction using Deep Generative Models","arxiv_id":"2012.04567","date":"2020-12-08","proceeding":null,"authors":["Razvan V Marinescu","Daniel Moyer","Polina Golland"],"abstract":"Machine learning models are commonly trained end-to-end and in a supervised setting, using paired (input, output) data. Examples include recent super-resolution methods that train on pairs of (low-resolution, high-resolution) images. However, these end-to-end approaches require re-training every time there is a distribution shift in the inputs (e.g., night images vs daylight) or relevant latent variables (e.g., camera blur or hand motion). In this work, we leverage state-of-the-art (SOTA) generative models (here StyleGAN2) for building powerful image priors, which enable application of Bayes' theorem for many downstream reconstruction tasks. Our method, Bayesian Reconstruction through Generative Models (BRGM), uses a single pre-trained generator model to solve different image restoration tasks, i.e., super-resolution and in-painting, by combining it with different forward corruption models. We keep the weights of the generator model fixed, and reconstruct the image by estimating the Bayesian maximum a-posteriori (MAP) estimate over the input latent vector that generated the reconstructed image. We further use variational inference to approximate the posterior distribution over the latent vectors, from which we sample multiple solutions. We demonstrate BRGM on three large and diverse datasets: (i) 60,000 images from the Flick Faces High Quality dataset (ii) 240,000 chest X-rays from MIMIC III and (iii) a combined collection of 5 brain MRI datasets with 7,329 scans. Across all three datasets and without any dataset-specific hyperparameter tuning, our simple approach yields performance competitive with current task-specific state-of-the-art methods on super-resolution and in-painting, while being more generalisable and without requiring any training. Our source code and pre-trained models are available online: https://razvanmarinescu.github.io/brgm/.","url_abs":"https://arxiv.org/abs/2012.04567v5","url_pdf":"https://arxiv.org/pdf/2012.04567v5.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":"bayesian-image-reconstruction-using-deep","repo_url":"https://github.com/razvanmarinescu/brgm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"bayesian-image-reconstruction-using-deep","repo_url":"https://github.com/razvanmarinescu/brgm-pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"image-denoising","task_name":"Image Denoising"},{"task_slug":"image-inpainting","task_name":"Image Inpainting"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"image-restoration","task_name":"Image Restoration"},{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"path-length-regularization","method_name":"Path Length Regularization"},{"method_slug":"r1-regularization","method_name":"R1 Regularization"},{"method_slug":"stylegan2","method_name":"StyleGAN2"},{"method_slug":"variational-inference","method_name":"Variational Inference"},{"method_slug":"weight-demodulation","method_name":"Weight Demodulation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-denoising-on-ffhq","task":"Image Denoising","dataset":"FFHQ","model":"BRGM","rank_in_archive_order":1,"of":1,"metrics":{"LPIPS":"0.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-denoising-on-ffhq-64x64-4x-upscaling","task":"Image Denoising","dataset":"FFHQ 64x64 - 4x upscaling","model":"BRGM","rank_in_archive_order":1,"of":1,"metrics":{"LPIPS":"0.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-inpainting-on-ffhq-1024-x-1024","task":"Image Inpainting","dataset":"FFHQ 1024 x 1024","model":"BRGM","rank_in_archive_order":1,"of":2,"metrics":{"LPIPS":"0.19","PSNR":"21.33","RMSE":"24.28","SSIM":"0.84"},"uses_additional_data":false},{"leaderboard":"/sota/image-inpainting-on-ffhq-1024-x-1024","task":"Image Inpainting","dataset":"FFHQ 1024 x 1024","model":"SN-PatchGAN","rank_in_archive_order":2,"of":2,"metrics":{"LPIPS":"0.24","PSNR":"19.67","RMSE":"30.75","SSIM":"0.82"},"uses_additional_data":false},{"leaderboard":"/sota/image-super-resolution-on-ffhq-256-x-256-4x","task":"Image Super-Resolution","dataset":"FFHQ 256 x 256 - 4x upscaling","model":"BRGM","rank_in_archive_order":10,"of":11,"metrics":{"PSNR":"24.16","SSIM":"0.70"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.04567","atlas_url":"https://app.syntology.ai/?focus=2012.04567","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2012.04567"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.04567\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.04567"},"call":"get_concepts_for_paper(arxiv_id=\"2012.04567\")"}],"by_repo":[{"repo":"razvanmarinescu/brgm","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"razvanmarinescu/brgm-pytorch","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"57f42f32942d03b964cab35fb6083a03e022451730d77963e6c0e672dc91f203","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}