Burst image processing is becoming increasingly popular in recent years. However, it is a challenging task since individual burst images undergo multiple degradations and often have mutual misalignments resulting in ghosting and zipper artifacts. Existing burst restoration methods usually do not consider the mutual correlation and non-local contextual information among burst frames, which tends to limit these approaches in challenging cases. Another key challenge lies in the robust up-sampling of burst frames. The existing up-sampling methods cannot effectively utilize the advantages of single-stage and progressive up-sampling strategies with conventional and/or recent up-samplers at the same time. To address these challenges, we propose a novel Gated Multi-Resolution Transfer Network (GMTNet) to reconstruct a spatially precise high-quality image from a burst of low-quality raw images. GMTNet consists of three modules optimized for burst processing tasks: Multi-scale Burst Feature Alignment (MBFA) for feature denoising and alignment, Transposed-Attention Feature Merging (TAFM) for multi-frame feature aggregation, and Resolution Transfer Feature Up-sampler (RTFU) to up-scale merged features and construct a high-quality output image. Detailed experimental analysis on five datasets validates our approach and sets a state-of-the-art for burst super-resolution, burst denoising, and low-light burst enhancement.
翻译:爆发式图像处理近年来变得越来越流行。然而,这是一项具有挑战性的任务,因为单个爆发式图像经历多种退化,并且往往存在相互错位导致出现残影和拉链伪影。现有的爆发式恢复方法通常不考虑爆炸帧之间的相互相关性和非局部上下文信息,这往往会限制这些方法在具有挑战性的情况下的应用。另一个关键的挑战在于爆发式帧的强大上采样。现有的上采样方法不能有效地利用单阶段和渐进上采样策略以及传统和/或最近的上采样器的优势。为了解决这些挑战,我们提出了一种新颖的闸门式多分辨率传递网络(GMTNet)来从低质量的原始图像爆发中重构出空间精度高的高质量图像。GMTNet由三个针对爆发处理任务而优化的模块组成:用于特征去噪和对齐的多尺度爆发特征对齐(MBFA),用于多帧特征聚合的传递-注意力特征融合(TAFM),以及用于提高合并特征并构建高品质输出图像的分辨率转移特征上采样器(RTFU)。对五个数据集的详细实验分析验证了我们的方法,并为爆发超分辨率,爆发降噪和低光爆发增强设定了最新技术标准。