Conditional Perceptual Quality Preserving Image Compression
This work addresses the need for more flexible and high-quality image compression methods for users who require control over perceptual aspects, though it is incremental as it builds on existing perceptual quality theories.
The authors tackled the problem of image compression by extending perceptual quality to a conditional form based on user-defined side information, and they proposed an optimal compression framework that maintains high perceptual and semantic quality across all bitrates, with experimental results demonstrating its effectiveness.
We propose conditional perceptual quality, an extension of the perceptual quality defined in \citet{blau2018perception}, by conditioning it on user defined information. Specifically, we extend the original perceptual quality $d(p_{X},p_{\hat{X}})$ to the conditional perceptual quality $d(p_{X|Y},p_{\hat{X}|Y})$, where $X$ is the original image, $\hat{X}$ is the reconstructed, $Y$ is side information defined by user and $d(.,.)$ is divergence. We show that conditional perceptual quality has similar theoretical properties as rate-distortion-perception trade-off \citep{blau2019rethinking}. Based on these theoretical results, we propose an optimal framework for conditional perceptual quality preserving compression. Experimental results show that our codec successfully maintains high perceptual quality and semantic quality at all bitrate. Besides, by providing a lowerbound of common randomness required, we settle the previous arguments on whether randomness should be incorporated into generator for (conditional) perceptual quality compression. The source code is provided in supplementary material.