This document summarizes recent advances in single image super-resolution (SISR) using deep learning methods. It discusses early SISR networks like SRCNN, VDSR and ESPCN. SRResNet is presented as a baseline method, incorporating residual blocks and pixel shuffle upsampling. SRGAN and EDSR are also introduced, with EDSR achieving state-of-the-art PSNR results. The relationship between reconstruction loss, perceptual quality and distortion is examined. While PSNR improves yearly, a perception-distortion tradeoff remains. Developments are ongoing to produce outputs that are both accurately restored and naturally perceived.
This document summarizes recent advances in single image super-resolution (SISR) using deep learning methods. It discusses early SISR networks like SRCNN, VDSR and ESPCN. SRResNet is presented as a baseline method, incorporating residual blocks and pixel shuffle upsampling. SRGAN and EDSR are also introduced, with EDSR achieving state-of-the-art PSNR results. The relationship between reconstruction loss, perceptual quality and distortion is examined. While PSNR improves yearly, a perception-distortion tradeoff remains. Developments are ongoing to produce outputs that are both accurately restored and naturally perceived.
文献紹介:Selective Feature Compression for Efficient Activity Recognition InferenceToru Tamaki
Chunhui Liu, Xinyu Li, Hao Chen, Davide Modolo, Joseph Tighe; Selective Feature Compression for Efficient Activity Recognition Inference, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 13628-13637
https://openaccess.thecvf.com/content/ICCV2021/html/Liu_Selective_Feature_Compression_for_Efficient_Activity_Recognition_Inference_ICCV_2021_paper.html
ImageJ is an open-source image processing program originally created in 1987 as NIH Image. It was later rewritten in Java as ImageJ in 1997. Key features include support for a wide range of image formats, macro scripting, plugins, and its use in scientific image analysis. ImageJ is widely used for tasks like particle analysis, image segmentation, image enhancement, and more. It has a large user community and active development of new plugins and extensions.
This document discusses sparse coding super-resolution (ScSR) for single-frame super-resolution of medical images. ScSR uses a sparse representation prior to reconstruct high-resolution images from low-resolution inputs. The document evaluates ScSR on SPECT images with and without additional anatomical information. ScSR improved image quality over bilinear interpolation as measured by higher PSNR scores and recovered finer details in power spectral density analysis. Adding computed tomography, magnetic resonance, or digital phantom data provided negligible further improvement over ScSR alone.
2. Disclosure of conflict of interest
We have nothing to declare for this study.
the 77th Annual Meeting of the JSRT
Japanese Society of Radiological
Technology