Unified learning-based lossy and lossless JPEG recompression
This addresses the need for efficient compression of existing JPEG images, which is a domain-specific incremental improvement over prior methods that only handled lossless recompression.
The paper tackles the problem of compressing already JPEG-compressed images by proposing a unified framework for both lossy and lossless JPEG recompression, achieving arbitrarily low distortion when bitrate approaches the lossless compression upper bound.
JPEG is still the most widely used image compression algorithm. Most image compression algorithms only consider uncompressed original image, while ignoring a large number of already existing JPEG images. Recently, JPEG recompression approaches have been proposed to further reduce the size of JPEG files. However, those methods only consider JPEG lossless recompression, which is just a special case of the rate-distortion theorem. In this paper, we propose a unified lossly and lossless JPEG recompression framework, which consists of learned quantization table and Markovian hierarchical variational autoencoders. Experiments show that our method can achieve arbitrarily low distortion when the bitrate is close to the upper bound, namely the bitrate of the lossless compression model. To the best of our knowledge, this is the first learned method that bridges the gap between lossy and lossless recompression of JPEG images.