Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by up to 0.14~0.45dB, while the total number of parameters can be reduced by up to 67%. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). I shall give you the abstract technical info it says about the model. Yes the lack of color noise and artifacts is what stood out to me, and the consistency of the small scale detail.
0 kommentar(er)
