"Zero-Shot" Super-Resolution using Deep Internal Learning

17 Dec 2017Assaf ShocherNadav CohenMichal Irani

Deep Learning has led to a dramatic leap in Super-Resolution (SR) performance in the past few years. However, being supervised, these SR methods are restricted to specific training data, where the acquisition of the low-resolution (LR) images from their high-resolution (HR) counterparts is predetermined (e.g., bicubic downscaling), without any distracting artifacts (e.g., sensor noise, image compression, non-ideal PSF, etc)... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Super-Resolution BSD100 - 4x upscaling ZSSR PSNR 27.12 # 30
SSIM 0.7211 # 34
Image Super-Resolution Set14 - 4x upscaling ZSSR PSNR 28.01 # 33
SSIM 0.7651 # 38
Image Super-Resolution Set5 - 4x upscaling ZSSR PSNR 31.13 # 30
SSIM 0.8796 # 33

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet