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.
[2010]
Large-scale Image Classification: Fast Feature Extraction and SVM Training
[2011]
High-dimensional signature compression for large-scale image classification
Domain Adaptive Faster R-CNN for Object Detection in the Wild 論文紹介Tsukasa Takagi
Domain Adaptive Faster R-CNN for Object Detection in the Wild
第46回 コンピュータビジョン勉強会@関東 CVPR2018読み会(前編)にて発表したスライドです。
https://kantocv.connpass.com/event/88613/
The document contains a date, 1615, repeated twice. There is no other text or context provided, so a summary is not possible based on the extremely limited information given.