Perceptual Losses for Real-Time Style Transfer and Super-Resolution
Lists
Only you see this
Abstract
We consider image transformation problems, where an input image is transformed into an output image. Recent methods for such problems typically train feed-forward convolutional neural networks using a \emph{per-pixel} loss between the output and ground-truth images. Parallel work has shown that high-quality images can be generated by defining and optimizing \emph{perceptual} loss functions based on high-level features extracted from pretrained networks. We combine the benefits of both approaches, and propose the use of perceptual loss functions for training feed-forward networks for image transformation tasks. We show results on image style transfer, where a feed-forward network is trained to solve the optimization problem proposed by Gatys et al in real-time. Compared to the optimization-based method, our network gives similar qualitative results but is three orders of magnitude faster. We also experiment with single-image super-resolution, where replacing a per-pixel loss with a perceptual loss gives visually pleasing results.
BibTeX
@inproceedings{johnson2016perceptual,
author = {Justin Johnson and Alexandre Alahi and Li Fei-Fei},
title = {{Perceptual Losses for Real-Time Style Transfer and Super-Resolution}},
booktitle = {European Conference on Computer Vision},
year = {2016},
doi = {10.1007/978-3-319-46475-6\_43},
}| Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | arXiv · 2016 |
| ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks | Workshops @ ECCV · 2018 |
| Image Style Transfer Using Convolutional Neural Networks | CVPR · 2016 |
| Semantic Image Inpainting with Deep Generative Models | arXiv · 2016 |
| Improving Perceptual Loss with CLIP for Super-Resolution | Journal of the Japan Society for Precision Engineering · 2024 |
| Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN | arXiv · 2022 |