{"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/bayesian-enhancement-models-for-one-to-many","title":"Bayesian Enhancement Models for One-to-Many Mapping in Image Enhancement","arxiv_id":null,"date":"2024-10-13","proceeding":"Anonymous ICLR Submission 2024 10","authors":["Anonymous"],"abstract":"Image enhancement is considered an ill-posed inverse problem due to its tendency to have multiple solutions. The loss of information makes accurately reconstructing the original image from observed data challenging. Also, the quality of the result is often subjective to individual preferences. This obviously poses a one-to-many mapping challenge. To address this, we propose a Bayesian Enhancement Model (BEM) that leverages Bayesian estimation to capture inherent uncertainty and accommodate diverse outputs. Our approach, integrated within a two-stage framework, first employs a Bayesian Neural Network (BNN) to model reduced-dimensional image representations, followed by a deterministic network for refinement. We further introduce a dynamic \\emph{Momentum Prior} to overcome convergence issues typically faced by BNNs in high-dimensional spaces. Extensive experiments across multiple low-light and underwater image enhancement benchmarks demonstrate the superiority of our method over traditional deterministic models, particularly in real-world applications lacking reference images, highlighting the potential of Bayesian models in handling one-to-many mapping problems.","url_abs":"https://openreview.net/forum?id=jJJOoLVAEm","url_pdf":"https://openreview.net/pdf?id=jJJOoLVAEm","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-enhancement-models-for-one-to-many","repo_url":"https://github.com/Anonymous1563/Bayesian-Enhancement-Model","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-enhancement","task_name":"Image Enhancement"},{"task_slug":"low-light-image-enhancement","task_name":"Low-Light Image Enhancement"},{"task_slug":"underwater-image-restoration","task_name":"Underwater Image Restoration"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/low-light-image-enhancement-on-dicm","task":"Low-Light Image Enhancement","dataset":"DICM","model":"BEM","rank_in_archive_order":2,"of":6,"metrics":{"NIQE":"3.55"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-lime","task":"Low-Light Image Enhancement","dataset":"LIME","model":"BEM","rank_in_archive_order":2,"of":6,"metrics":{"NIQE":"3.56"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-lol","task":"Low-Light Image Enhancement","dataset":"LOL","model":"BEM_","rank_in_archive_order":2,"of":40,"metrics":{"Average PSNR":"28.80","LPIPS":"0.069","SSIM":"0.884"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-lol","task":"Low-Light Image Enhancement","dataset":"LOL","model":"BEM","rank_in_archive_order":12,"of":40,"metrics":{"Average PSNR":"26.83","LPIPS":"0.072","SSIM":"0.877"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-mef","task":"Low-Light Image Enhancement","dataset":"MEF","model":"BEM","rank_in_archive_order":2,"of":7,"metrics":{"NIQE":"3.14"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-npe","task":"Low-Light Image Enhancement","dataset":"NPE","model":"BEM","rank_in_archive_order":2,"of":6,"metrics":{"NIQE":" 3.72"},"uses_additional_data":false},{"leaderboard":"/sota/low-light-image-enhancement-on-vv","task":"Low-Light Image Enhancement","dataset":"VV","model":"BEM","rank_in_archive_order":2,"of":7,"metrics":{"NIQE":"2.91"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}