论文标题
图像修复的简单基线
Simple Baselines for Image Restoration
论文作者
论文摘要
尽管最近在图像恢复领域取得了重大进展，但最新方法（SOTA）方法的系统复杂性也在增加，这可能会阻碍方法的方便分析和比较。在本文中，我们提出了一个超过SOTA方法并且在计算上有效的简单基线。为了进一步简化基线，我们揭示了非线性激活功能，例如Sigmoid，Relu，Gelu，SoftMax等不需要：可以用乘法代替或去除。因此，我们从基线得出一个非线性无线激活网络，即NAFNET。在各种具有挑战性的基准上取得了SOTA结果，例如33.69 db psnr在GoPro上（用于图像脱毛），超过了先前的SOTA 0.38 dB，其计算成本仅为8.4％； SIDD上的40.30 dB PSNR（用于图像denoising），超过了先前的SOTA 0.28 dB，其计算成本不到一半。代码和预训练的模型将在https://github.com/megvii-research/nafnet上发布。
Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods. In this paper, we propose a simple baseline that exceeds the SOTA methods and is computationally efficient. To further simplify the baseline, we reveal that the nonlinear activation functions, e.g. Sigmoid, ReLU, GELU, Softmax, etc. are not necessary: they could be replaced by multiplication or removed. Thus, we derive a Nonlinear Activation Free Network, namely NAFNet, from the baseline. SOTA results are achieved on various challenging benchmarks, e.g. 33.69 dB PSNR on GoPro (for image deblurring), exceeding the previous SOTA 0.38 dB with only 8.4% of its computational costs; 40.30 dB PSNR on SIDD (for image denoising), exceeding the previous SOTA 0.28 dB with less than half of its computational costs. The code and the pre-trained models are released at https://github.com/megvii-research/NAFNet.
