In order to get raw images of high quality for downstream Image Signal Process (ISP), in this paper we present an Efficient Locally Multiplicative Transformer called ELMformer for raw image restoration. ELMformer contains two core designs especially for raw images whose primitive attribute is single-channel. The first design is a Bi-directional Fusion Projection (BFP) module, where we consider both the color characteristics of raw images and spatial structure of single-channel. The second one is that we propose a Locally Multiplicative Self-Attention (L-MSA) scheme to effectively deliver information from the local space to relevant parts. ELMformer can efficiently reduce the computational consumption and perform well on raw image restoration tasks. Enhanced by these two core designs, ELMformer achieves the highest performance and keeps the lowest FLOPs on raw denoising and raw deblurring benchmarks compared with state-of-the-arts. Extensive experiments demonstrate the superiority and generalization ability of ELMformer. On SIDD benchmark, our method has even better denoising performance than ISP-based methods which need huge amount of additional sRGB training images. The codes are release at https://github.com/leonmakise/ELMformer.
翻译:为了获得下游图像信号进程高质量原始图像,本文件中我们提出了一个高效本地多复制变异器(ELMA)计划,名为 ELMEx, 用于原始图像恢复。 ELMEx 包含两个核心设计, 特别是原始属性为单通道的原始图像。 第一个设计是双向融合投影模块, 我们既考虑原始图像的颜色特征,也考虑单通道的空间结构。 第二个是我们提出一个本地多复制自控(L-MSA)计划, 将信息从本地空间有效传送到相关部分。 ELMA 计划可以有效减少计算消耗量, 并完成原始图像恢复任务。 通过这两个核心设计, ELMExect 实现了最高性能, 并将最低FLOPs 的原始分解和原始分流基准与艺术状态相比较。 广泛的实验展示了ELMADD 的优势和普及能力。 关于SIDDD 基准, 我们的方法比基于 ISP-MAUD / 的图像解析方法要更好进行分辨。 在基于 ISMUB / aredustruction 需要巨型 SGRGRGL 的图像数量的系统培训。