Abstract
Burst image restoration aims to reconstruct a high-quality image from burst images, which are typically captured using manually designed exposure settings. Although these exposure settings significantly influence the final restoration performance, the problem of finding optimal exposure settings has been overlooked. In this paper, we present Dynamic Exposure Burst Image Restoration (DEBIR), a novel burst image restoration pipeline that enhances restoration quality by dynamically predicting exposure times tailored to the shooting environment. In our pipeline, Burst Auto-Exposure Network (BAENet) estimates the optimal exposure time for each burst image based on a preview image, as well as motion magnitude and gain. Subsequently, a burst image restoration network reconstructs a high-quality image from burst images captured using these optimal exposure times. For training, we introduce a differentiable burst simulator and a three-stage training strategy. Our experiments demonstrate that our pipeline achieves state-of-the-art restoration quality. Furthermore, we validate the effectiveness of our approach on a real-world camera system, demonstrating its practicality.
Abstract (translated)
连拍图像恢复旨在从通常采用手动设计曝光参数拍摄的连拍图像中重建高质量图像。尽管这些曝光参数会显著影响最终恢复效果，但寻找最优曝光参数的问题却一直未被重视。本文提出动态曝光连拍图像恢复（DEBIR）这一新颖的连拍图像恢复流程，通过动态预测适应拍摄环境的最佳曝光时间来提升恢复质量。在该流程中，连拍自动曝光网络（BAENet）基于预览图像以及运动幅度和增益，为每张连拍图像估算最优曝光时间。随后，连拍图像恢复网络利用这些最优曝光时间拍摄的连拍图像重建高质量图像。为进行训练，我们引入了可微分连拍模拟器和三阶段训练策略。实验表明，我们的流程达到了最先进的恢复质量。此外，我们还在真实相机系统上验证了方法的有效性，证明了其实用性。
URL
https://arxiv.org/abs/2603.21784
