FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3196057788> ?p ?o ?g. }

• W3196057788 abstract "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). 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. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. 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. 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. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by $textbf{up to 0.14$sim$0.45dB}$, while the total number of parameters can be reduced by $textbf{up to 67%}$." @default.
• W3196057788 created "2021-08-30" @default.
• W3196057788 creator A5001254143 @default.
• W3196057788 creator A5003850660 @default.
• W3196057788 creator A5010215983 @default.
• W3196057788 creator A5052236177 @default.
• W3196057788 creator A5059644827 @default.
• W3196057788 creator A5090145580 @default.
• W3196057788 date "2021-08-23" @default.
• W3196057788 modified "2023-10-18" @default.
• W3196057788 title "SwinIR: Image Restoration Using Swin Transformer" @default.
• W3196057788 cites W1578089973 @default.
• W3196057788 cites W1791560514 @default.
• W3196057788 cites W1906770428 @default.
• W3196057788 cites W1912194039 @default.
• W3196057788 cites W2047920195 @default.
• W3196057788 cites W2048695508 @default.
• W3196057788 cites W2056370875 @default.
• W3196057788 cites W2099471712 @default.
• W3196057788 cites W2121927366 @default.
• W3196057788 cites W2126926806 @default.
• W3196057788 cites W2128254161 @default.
• W3196057788 cites W2135065661 @default.
• W3196057788 cites W2142683286 @default.
• W3196057788 cites W2150081556 @default.
• W3196057788 cites W2167191464 @default.
• W3196057788 cites W2242218935 @default.
• W3196057788 cites W2331128040 @default.
• W3196057788 cites W2476548250 @default.
• W3196057788 cites W2508457857 @default.
• W3196057788 cites W2607041014 @default.
• W3196057788 cites W2613155248 @default.
• W3196057788 cites W2626778328 @default.
• W3196057788 cites W2741137940 @default.
• W3196057788 cites W2805163084 @default.
• W3196057788 cites W2866634454 @default.
• W3196057788 cites W2890584119 @default.
• W3196057788 cites W2891158090 @default.
• W3196057788 cites W2914992179 @default.
• W3196057788 cites W2919720707 @default.
• W3196057788 cites W2922435819 @default.
• W3196057788 cites W2947156405 @default.
• W3196057788 cites W2949718784 @default.
• W3196057788 cites W2950217418 @default.
• W3196057788 cites W2952773607 @default.
• W3196057788 cites W2954930822 @default.
• W3196057788 cites W2962935103 @default.
• W3196057788 cites W2963372104 @default.
• W3196057788 cites W2963470893 @default.
• W3196057788 cites W2963494934 @default.
• W3196057788 cites W2963645458 @default.
• W3196057788 cites W2963729050 @default.
• W3196057788 cites W2964125708 @default.
• W3196057788 cites W2964277374 @default.
• W3196057788 cites W2971719842 @default.
• W3196057788 cites W2987869089 @default.
• W3196057788 cites W2988916019 @default.
• W3196057788 cites W2994759459 @default.
• W3196057788 cites W3000775737 @default.
• W3196057788 cites W3009428327 @default.
• W3196057788 cites W3011456574 @default.
• W3196057788 cites W3033210410 @default.
• W3196057788 cites W3034785019 @default.
• W3196057788 cites W3035413931 @default.
• W3196057788 cites W3038857985 @default.
• W3196057788 cites W3094502228 @default.
• W3196057788 cites W3095671795 @default.
• W3196057788 cites W3096609285 @default.
• W3196057788 cites W3096739052 @default.
• W3196057788 cites W3104028135 @default.
• W3196057788 cites W3109737331 @default.
• W3196057788 cites W3116489684 @default.
• W3196057788 cites W3129817135 @default.
• W3196057788 cites W3135921327 @default.
• W3196057788 cites W3138516171 @default.
• W3196057788 cites W3154723007 @default.
• W3196057788 cites W3156811085 @default.
• W3196057788 cites W3160284783 @default.
• W3196057788 cites W3164705069 @default.
• W3196057788 cites W3164815015 @default.
• W3196057788 cites W3164972083 @default.
• W3196057788 cites W3166368936 @default.
• W3196057788 cites W3167568784 @default.
• W3196057788 cites W3168684807 @default.
• W3196057788 cites W3169612303 @default.
• W3196057788 cites W3170666462 @default.
• W3196057788 cites W3170841864 @default.
• W3196057788 cites W3171125843 @default.
• W3196057788 cites W3172345956 @default.
• W3196057788 cites W3174060721 @default.
• W3196057788 cites W3175544090 @default.
• W3196057788 cites W3184190059 @default.
• W3196057788 cites W3184726201 @default.
• W3196057788 cites W3202167470 @default.
• W3196057788 cites W3202903235 @default.
• W3196057788 cites W3203631022 @default.
• W3196057788 cites W54257720 @default.
• W3196057788 doi "https://doi.org/10.48550/arxiv.2108.10257" @default.
• W3196057788 hasPublicationYear "2021" @default.
• W3196057788 type Work @default.

• next