CVJan 24, 2025

Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement

arXiv:2501.14265v27 citationsh-index: 23
Originality Incremental advance
AI Analysis

This addresses the problem of handling uncertainty in image enhancement for applications like low-light and underwater photography, though it appears incremental by combining existing BNN and DNN techniques.

The paper tackles the one-to-many mapping challenge in image enhancement, where degraded images can have multiple plausible outputs, by proposing a Bayesian Enhancement Model (BEM) that uses Bayesian Neural Networks to capture uncertainty and produce diverse results, achieving superior performance over deterministic models on benchmarks.

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 Momentum Prior. Extensive experiments on multiple low-light and underwater image enhancement benchmarks demonstrate the superiority of our method over deterministic models.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes