# Learning a Reinforced Agent for Flexible Exposure Bracketing Selection

arXiv: https://arxiv.org/abs/2005.12536 · HTML: https://mlsanity.com/paper/2005.12536/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2020.

## Built on by (most cited first, 6 of 6)

- [Spatially Varying Exposure with 2-by-2 Multiplexing: Optimality and Universality](https://mlsanity.com/paper/2306.17367/) (2023)
- [DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning](https://mlsanity.com/paper/2207.03081/) (2022)
- [DRHDR: A Dual branch Residual Network for Multi-Bracket High Dynamic Range Imaging](https://mlsanity.com/paper/2206.04124/) (2022)
- [AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes](https://mlsanity.com/paper/2508.13503/) (2025)
- [Dual Exposure Stereo for Extended Dynamic Range 3D Imaging](https://mlsanity.com/paper/2412.02351/) (2024)
- [Dynamic Exposure Burst Image Restoration](https://mlsanity.com/paper/2603.21784/) (2026)

## Abstract (arXiv)

Automatically selecting exposure bracketing (images exposed differently) is important to obtain a high dynamic range image by using multi-exposure fusion. Unlike previous methods that have many restrictions such as requiring camera response function, sensor noise model, and a stream of preview images with different exposures (not accessible in some scenarios e.g. some mobile applications), we propose a novel deep neural network to automatically select exposure bracketing, named EBSNet, which is sufficiently flexible without having the above restrictions. EBSNet is formulated as a reinforced agent that is trained by maximizing rewards provided by a multi-exposure fusion network (MEFNet). By utilizing the illumination and semantic information extracted from just a single auto-exposure preview image, EBSNet can select an optimal exposure bracketing for multi-exposure fusion. EBSNet and MEFNet can be jointly trained to produce favorable results against recent state-of-the-art approaches. To facilitate future research, we provide a new benchmark dataset for multi-exposure selection and fusion.