Learned Image Downscaling for Upscaling using Content Adaptive Resampler

22 Jul 2019Wanjie SunZhenzhong Chen

Deep convolutional neural network based image super-resolution (SR) models have shown superior performance in recovering the underlying high resolution (HR) images from low resolution (LR) images obtained from the predefined downscaling methods. In this paper we propose a learned image downscaling method based on content adaptive resampler (CAR) with consideration on the upscaling process... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Super-Resolution BSD100 - 2x upscaling CAR PSNR 33.83 # 1
Image Super-Resolution BSD100 - 4x upscaling CAR PSNR 29.15 # 1
Image Super-Resolution DIV2K val - 2x upscaling CAR PSNR 38.26 # 1
Image Super-Resolution DIV2K val - 4x upscaling CAR PSNR 32.82 # 1
Image Super-Resolution Set14 - 2x upscaling CAR PSNR 35.61 # 1
Image Super-Resolution Set14 - 4x upscaling CAR PSNR 30.31 # 1
Image Super-Resolution Set5 - 2x upscaling CAR PSNR 38.94 # 1
Image Super-Resolution Set5 - 4x upscaling CAR PSNR 33.88 # 1
Image Super-Resolution Urban100 - 2x upscaling CAR PSNR 35.24 # 1
Image Super-Resolution Urban100 - 4x upscaling CAR PSNR 29.28 # 1