Learned Lossless Compression for JPEG via Frequency-Domain Prediction
This addresses storage and transmission efficiency for large-scale JPEG image datasets, representing an incremental improvement over existing methods.
The paper tackles the problem of further compressing JPEG images by proposing a learned lossless compression framework that predicts DCT coefficient distributions in the frequency domain, achieving superior or comparable performance to recent handcrafted compressors.
JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing distribution of DCT coefficients and raw pixels. In this paper, we propose a novel framework for learned lossless compression of JPEG images that achieves end-to-end optimized prediction of the distribution of decoded DCT coefficients. To enable learning in the frequency domain, DCT coefficients are partitioned into groups to utilize implicit local redundancy. An autoencoder-like architecture is designed based on the weight-shared blocks to realize entropy modeling of grouped DCT coefficients and independently compress the priors. We attempt to realize learned lossless compression of JPEG images in the frequency domain. Experimental results demonstrate that the proposed framework achieves superior or comparable performance in comparison to most recent lossless compressors with handcrafted context modeling for JPEG images.