Conditional Perceptual Quality Preserving Image Compression

We propose conditional perceptual quality, an extension of the perceptual quality defined in citetblau2018perception, by conditioning it on user defined information. Specifically, we extend the original perceptual quality d(pX,p_hatX) to the conditional perceptual quality d(pX|Y,p_hatX|Y), where X is the original image, hatX 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 citepblau2019rethinking. 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.