Learned perceptual image enhancement
By Hossein Talebi Esfandarani, Peyman Milanfar. 2017
82 citations recorded by the source corpus.
Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images. While L1 and L2 losses are perhaps the most widely used functions for this purpose, they do not necessarily lead to perceptually compelling results. In this paper, we show that adding a learned no-reference image quality metric to the loss can significantly improve enhancement operators. This metric is implemented using a CNN (convolutional neural network) trained on a large-scale dataset labelled with aesthetic preferences ofhuman raters. This loss allows us to conveniently perform back-propagation in our learning framework to simultaneously optimize for similarity to a given ground truth reference and perceptual quality. This perceptual loss is only used to train parameters of image processing operators, and does not impose any extra complexity at inference time. Our experiments demonstrate that this loss can be effective for tuning a variety of operators such as local tone mapping and dehazing.
Subfields: Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Dacheng Tao
- Alexei A. Efros
- Richard Zhang
- Trevor Darrell
- Jitendra Malik
- Antonio Torralba
Citations in the corpus
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric (2018, background): “Concurrent work by Talebi and Milanfar [53, 54] train a deep network in the context of NR-IQA for image aesthetics.”
- NIMA: Neural Image Assessment (2017, background): “A more detailed treatment is presented in [23].”