Modeling Image Quantization Tradeoffs for Optimal Compression
This work addresses the need for improved compression efficiency in image processing, though it appears incremental as it builds on existing quantization methods with a novel optimization approach.
The paper tackles the problem of optimizing quantization tables for lossy image compression by proposing a deep learning method that uses a minimax loss function to better balance rate-distortion tradeoffs, achieving stronger performance through cross-channel information loss measurement.
All Lossy compression algorithms employ similar compression schemes -- frequency domain transform followed by quantization and lossless encoding schemes. They target tradeoffs by quantizating high frequency data to increase compression rates which come at the cost of higher image distortion. We propose a new method of optimizing quantization tables using Deep Learning and a minimax loss function that more accurately measures the tradeoffs between rate and distortion parameters (RD) than previous methods. We design a convolutional neural network (CNN) that learns a mapping between image blocks and quantization tables in an unsupervised manner. By processing images across all channels at once, we can achieve stronger performance by also measuring tradeoffs in information loss between different channels. We initially target optimization on JPEG images but feel that this can be expanded to any lossy compressor.