Abstract
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, such as variations in illumination. This naturally results in a one-to-many mapping challenge. 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 achieve real-time inference, we introduce a two-stage approach: Stage I employs a BNN to model the one-to-many mappings in the low-dimensional space, while Stage II refines fine-grained image details using a Deterministic Neural Network (DNN). To accelerate BNN training and convergence, we introduce a dynamic \emph{Momentum Prior}. Extensive experiments on multiple low-light and underwater image enhancement benchmarks demonstrate the superiority of our method over deterministic models.
Abstract (translated)
在图像增强任务中，例如低光和水下图像增强，由于动态拍摄条件（如光照变化）的影响，一幅退化后的图像可能对应多个合理的目标图像。这自然导致了一个从一到多的映射挑战。为了解决这个问题，我们提出了一种贝叶斯增强模型（Bayesian Enhancement Model, BEM），该模型采用贝叶斯神经网络（Bayesian Neural Networks, BNNs）来捕捉数据不确定性并生成多样化的输出结果。 为了实现实时推理，我们引入了一个两阶段的方法：第一阶段使用BNN在低维空间中建模一到多的映射；第二阶段则利用确定性神经网络（Deterministic Neural Network, DNN）对图像中的细粒度细节进行精炼。为加速BNN的训练和收敛过程，我们提出了一种动态的“动量先验”(Momentum Prior)方法。 在多个低光和水下图像增强基准测试中进行的广泛实验表明，我们的方法优于确定性模型。
URL
https://arxiv.org/abs/2501.14265
