Abstract
In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images, researchers have attempted various image restoration and enhancement operations on photographs, including denoising, deblurring, and high dynamic range imaging. However, merely performing a single type of image enhancement still cannot yield satisfactory images. In this paper, to deal with the challenge above, we propose the Composite Refinement Network (CRNet) to address this issue using multiple exposure images. By fully integrating information-rich multiple exposure inputs, CRNet can perform unified image restoration and enhancement. To improve the quality of image details, CRNet explicitly separates and strengthens high and low-frequency information through pooling layers, using specially designed Multi-Branch Blocks for effective fusion of these frequencies. To increase the receptive field and fully integrate input features, CRNet employs the High-Frequency Enhancement Module, which includes large kernel convolutions and an inverted bottleneck ConvFFN. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge, surpassing previous SOTA models in both testing metrics and visual quality.
Abstract (translated)
在现实场景中，捕获的图像经常受到模糊、噪声和其他图像退化形式的影响，由于传感器限制，人们通常只能获得低动态范围图像。为了获得高质量的图像，研究人员对照片进行了各种图像修复和增强操作，包括去噪、去模糊和高动态范围成像。然而，仅进行一种图像增强操作仍然无法产生令人满意的图像。在本文中，为了应对上述挑战，我们提出了复合优化网络（CRNet）来解决这个问题，利用多个曝光图像。通过完全整合信息丰富的多个曝光输入，CRNet可以执行统一图像修复和增强。为了提高图像细节质量，CRNet通过池化层明确区分和加强高和低频信息，使用专门设计的Multi-Branch Blocks对这两个频率进行有效的融合。为了增加接收范围并完全整合输入特征，CRNet采用High-Frequency Enhancement Module，包括大内核卷积和反向瓶颈ConvFFN。我们的模型在Bracketing Image Restoration and Enhancement Challenge的第一 track获得了第三名的成绩，在测试指标和视觉质量方面均超过了之前的最佳模型。
URL
https://arxiv.org/abs/2404.14132
