EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correl...
Saved in:
Published in | 2017 IEEE International Conference on Computer Vision (ICCV) pp. 4501 - 4510 |
---|---|
Main Authors | , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.10.2017
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the human perception of image quality. As a result, algorithms minimizing these metrics tend to produce over-smoothed images that lack highfrequency textures and do not look natural despite yielding high PSNR values.,,We propose a novel application of automated texture synthesis in combination with a perceptual loss focusing on creating realistic textures rather than optimizing for a pixelaccurate reproduction of ground truth images during training. By using feed-forward fully convolutional neural networks in an adversarial training setting, we achieve a significant boost in image quality at high magnification ratios. Extensive experiments on a number of datasets show the effectiveness of our approach, yielding state-of-the-art results in both quantitative and qualitative benchmarks. |
---|---|
ISSN: | 2380-7504 |
DOI: | 10.1109/ICCV.2017.481 |