Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder

TL;DR

This paper introduces AEIC, a novel ultra-low bitrate image compression framework using shallow encoders and a diffusion decoder, achieving high perceptual quality and efficiency suitable for bandwidth-limited devices.

Contribution

The work presents a new ultra-low bitrate compression method with shallow encoders and a diffusion decoder, along with a feature distillation scheme to improve shallow encoder performance.

Findings

Outperforms existing methods in rate-distortion-perception at ultra-low bitrates

Achieves 35.8 FPS on 1080P images with competitive decoding speed

Maintains high perceptual fidelity with shallow encoder networks

Abstract

Ultra-low bitrate image compression (below 0.05 bits per pixel) is increasingly critical for bandwidth-constrained and computation-limited encoding scenarios such as edge devices. Existing frameworks typically rely on large pretrained encoders (e.g., VAEs or tokenizer-based models) and perform transform coding within their generative latent space. While these approaches achieve impressive perceptual fidelity, their reliance on heavy encoder networks makes them unsuitable for deployment on weak sender devices. In this work, we explore the feasibility of applying shallow encoders for ultra-low bitrate compression and propose a novel Asymmetric Extreme Image Compression (AEIC) framework that pursues simultaneously encoding simplicity and decoding quality. Specifically, AEIC employs moderate or even shallow encoder networks, while leveraging an one-step diffusion decoder to maintain high-fidelity and high-realism reconstructions under extreme bitrates. To further enhance the efficiency of shallow encoders, we design a dual-side feature distillation scheme that transfers knowledge from AEIC with moderate encoders to its shallow encoder variants. Experiments show that AEIC not only outperforms existing methods on rate-distortion-perception performance at ultra-low bitrates, but also delivers exceptional encoding efficiency for 35.8 FPS on 1080P images, while maintaining competitive decoding speed compared to existing methods. Code is available at https://github.com/LuizScarlet/AEIC.