Lossy Image Compression with Compressive Autoencoders

Lucas Theis , Wenzhe Shi , Andrew Cunningham , Ferenc Husz\'ar

Authors on Pith no claims yet

classification 📊 stat.ML cs.CV

keywords autoencoderscompressioncomputationallyimageimageslosslossyneed

read the original abstract

We propose a new approach to the problem of optimizing autoencoders for lossy image compression. New media formats, changing hardware technology, as well as diverse requirements and content types create a need for compression algorithms which are more flexible than existing codecs. Autoencoders have the potential to address this need, but are difficult to optimize directly due to the inherent non-differentiabilty of the compression loss. We here show that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs. Our network is furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images. This is in contrast to previous work on autoencoders for compression using coarser approximations, shallower architectures, computationally expensive methods, or focusing on small images.

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

Soft Anisotropic Diagrams for Differentiable Image Representation
cs.CV 2026-04 unverdicted novelty 7.0

SAD is a new explicit differentiable image representation based on soft anisotropic additively weighted Voronoi partitions that achieves higher PSNR and 4-19x faster training than Image-GS and Instant-NGP at matched bitrate.
Finite Scalar Quantization: VQ-VAE Made Simple
cs.CV 2023-09 conditional novelty 7.0

Finite scalar quantization simplifies VQ-VAE latents by independently rounding a few dimensions to fixed levels, producing an equivalent-sized implicit codebook with competitive performance and no collapse.
Cool-chic 5.0: Faster Encoding and Inter-Feature Entropy Modeling for Overfitted Image Compression
eess.IV 2026-05 unverdicted novelty 5.0

Cool-chic 5.0 delivers 11% lower rate than H.266/VVC and matches modern autoencoders like MLIC++ with 250 times lower decoding complexity through an updated decoder architecture and faster optimization for overfitted codecs.