Reversible Colour Density Compression of Images using cGANs
This work addresses the challenge of making color density compression practical for image processing applications, though it appears incremental as it builds on existing cGAN methods.
The paper tackled the problem of lossless decompression in image compression using color densities by employing conditional generative adversarial networks (cGANs) to learn a mapping between images and a loss function, resulting in visually lossless generations that indicate viable efficient color compression.
Image compression using colour densities is historically impractical to decompress losslessly. We examine the use of conditional generative adversarial networks in making this transformation more feasible, through learning a mapping between the images and a loss function to train on. We show that this method is effective at producing visually lossless generations, indicating that efficient colour compression is viable.