AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes

TL;DR

AdaptiveAE uses reinforcement learning to optimize shutter speed and ISO settings for HDR imaging in dynamic scenes, effectively balancing noise and motion blur to improve reconstruction quality.

Contribution

It introduces a novel reinforcement learning approach that adaptively selects exposure parameters considering motion blur and noise, outperforming traditional methods.

Findings

Achieves state-of-the-art HDR reconstruction quality.

Effectively balances noise and motion blur in dynamic scenes.

Adapts exposure sequences based on user-defined time budgets.

Abstract

Mainstream high dynamic range imaging techniques typically rely on fusing multiple images captured with different exposure setups (shutter speed and ISO). A good balance between shutter speed and ISO is crucial for achieving high-quality HDR, as high ISO values introduce significant noise, while long shutter speeds can lead to noticeable motion blur. However, existing methods often overlook the complex interaction between shutter speed and ISO and fail to account for motion blur effects in dynamic scenes. In this work, we propose AdaptiveAE, a reinforcement learning-based method that optimizes the selection of shutter speed and ISO combinations to maximize HDR reconstruction quality in dynamic environments. AdaptiveAE integrates an image synthesis pipeline that incorporates motion blur and noise simulation into our training procedure, leveraging semantic information and exposure histograms. It can adaptively select optimal ISO and shutter speed sequences based on a user-defined exposure time budget, and find a better exposure schedule than traditional solutions. Experimental results across multiple datasets demonstrate that it achieves the state-of-the-art performance.