Color Learning for Image Compression
This work addresses color fidelity in image compression for applications like video compression, but it is incremental as it builds on existing deep learning methods.
The paper tackles image compression by proposing a deep learning model with separate branches for luminance and chrominance, using CIEDE2000 in the loss function to improve color fidelity, and demonstrates performance benefits compared to other codecs.
Deep learning based image compression has gained a lot of momentum in recent times. To enable a method that is suitable for image compression and subsequently extended to video compression, we propose a novel deep learning model architecture, where the task of image compression is divided into two sub-tasks, learning structural information from luminance channel and color from chrominance channels. The model has two separate branches to process the luminance and chrominance components. The color difference metric CIEDE2000 is employed in the loss function to optimize the model for color fidelity. We demonstrate the benefits of our approach and compare the performance to other codecs. Additionally, the visualization and analysis of latent channel impulse response is performed.