Bayesian Enhancement Models for One-to-Many Mapping in Image Enhancement

ICLR 2025 Conference Submission1563 Authors

Keywords: Image Enhancement

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.
To address the noise in predictions of Bayesian Neural Networks (BNNs) for high-dimensional images, we propose a two-stage approach. The first stage utilises a BNN to model reduced-dimensional image representations, while the second stage employs a deterministic network to refine these representations.
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.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 1563