ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression

Autor: Zhi Li, Li-Heng Chen, Alan C. Bovik, Andrey Norkin, Christos G. Bampis
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Computer Science - Machine Learning
Image quality
Computer science
Computer Vision and Pattern Recognition (cs.CV)
media_common.quotation_subject
Computer Science - Computer Vision and Pattern Recognition
Video Recording
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
Machine Learning (cs.LG)
Image (mathematics)
Reduction (complexity)
Perception
Image Processing
Computer-Assisted
FOS: Electrical engineering
electronic engineering
information engineering
0202 electrical engineering
electronic engineering
information engineering
Humans
Quality (business)
Proxy (statistics)
media_common
Artificial neural network
Image and Video Processing (eess.IV)
Electrical Engineering and Systems Science - Image and Video Processing
Data Compression
Computer Graphics and Computer-Aided Design
020201 artificial intelligence & image processing
Neural Networks
Computer
Algorithm
Algorithms
Software
Image compression
Zdroj: IEEE Transactions on Image Processing. 30:360-373
ISSN: 1941-0042
1057-7149
DOI: 10.1109/tip.2020.3036752
Popis: The use of $\ell_p$ $(p=1,2)$ norms has largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess the loss of visual information, these simple norms are not very consistent with human perception. Here, we describe a different "proximal" approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, broadly termed ProxIQA, which mimics the perceptual model while serving as a loss layer of the network. We experimentally demonstrate how this optimization framework can be applied to train an end-to-end optimized image compression network. By building on top of an existing deep image compression model, we are able to demonstrate a bitrate reduction of as much as $31\%$ over MSE optimization, given a specified perceptual quality (VMAF) level.
Comment: 12 pages, 12 figures, 5 tables
Databáze: OpenAIRE
Externí odkaz: