On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework
arXiv:2106.02782
Abstract
Lossy compression algorithms are typically designed to achieve the lowest possible distortion at a given bit rate. However, recent studies show that pursuing high perceptual quality would lead to increase of the lowest achievable distortion (e.g., MSE). This paper provides nontrivial results theoretically revealing that, \textit{1}) the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion, \textit{2}) an optimal encoder for the "classic" rate-distortion problem is also optimal for the perceptual compression problem, \textit{3}) distortion loss is unnecessary for training a perceptual decoder. Further, we propose a novel training framework to achieve the lowest MSE distortion under perfect perception constraint at a given bit rate. This framework uses a GAN with discriminator conditioned on an MSE-optimized encoder, which is superior over the traditional framework using distortion plus adversarial loss. Experiments are provided to verify the theoretical finding and demonstrate the superiority of the proposed training framework.
arXiv commentICML 2021
References in corpus (6)
- Conditional Generative Adversarial Nets
- Neural Discrete Representation Learning
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
- The Perception-Distortion Tradeoff
- Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
- Rate-Distortion-Perception Tradeoff of Variable-Length Source Coding for General Information Sources