Saved in:
Bibliographic Details
Main Authors: Huang, Guoxi, Yang, Qirui, Lin, Ruirui, Qi, Zipeng, Bull, David, Anantrasirichai, Nantheera
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.14265
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918218067607552
author Huang, Guoxi
Yang, Qirui
Lin, Ruirui
Qi, Zipeng
Bull, David
Anantrasirichai, Nantheera
author_facet Huang, Guoxi
Yang, Qirui
Lin, Ruirui
Qi, Zipeng
Bull, David
Anantrasirichai, Nantheera
contents In image enhancement tasks, such as low-light and underwater image enhancement, a degraded image can correspond to multiple plausible target images due to dynamic photography conditions. This naturally results in a one-to-many mapping problem. To address this, we propose a Bayesian Enhancement Model (BEM) that incorporates Bayesian Neural Networks (BNNs) to capture data uncertainty and produce diverse outputs. To enable fast inference, we introduce a BNN-DNN framework: a BNN is first employed to model the one-to-many mapping in a low-dimensional space, followed by a Deterministic Neural Network (DNN) that refines fine-grained image details. Extensive experiments on multiple low-light and underwater image enhancement benchmarks demonstrate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14265
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement
Huang, Guoxi
Yang, Qirui
Lin, Ruirui
Qi, Zipeng
Bull, David
Anantrasirichai, Nantheera
Computer Vision and Pattern Recognition
In image enhancement tasks, such as low-light and underwater image enhancement, a degraded image can correspond to multiple plausible target images due to dynamic photography conditions. This naturally results in a one-to-many mapping problem. To address this, we propose a Bayesian Enhancement Model (BEM) that incorporates Bayesian Neural Networks (BNNs) to capture data uncertainty and produce diverse outputs. To enable fast inference, we introduce a BNN-DNN framework: a BNN is first employed to model the one-to-many mapping in a low-dimensional space, followed by a Deterministic Neural Network (DNN) that refines fine-grained image details. Extensive experiments on multiple low-light and underwater image enhancement benchmarks demonstrate the effectiveness of our method.
title Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.14265