Single-step Diffusion for Image Compression at Ultra-Low Bitrates
This addresses the issue of limited perceptual quality and prohibitive latency for users of generative codecs in image compression at low bitrates, representing an incremental improvement over prior diffusion-based methods.
The paper tackles the problem of severe quality degradation and slow decoding in image compression at ultra-low bitrates by proposing a single-step diffusion model, achieving comparable compression performance to state-of-the-art methods while improving decoding speed by about 50x.
Although there have been significant advancements in image compression techniques, such as standard and learned codecs, these methods still suffer from severe quality degradation at extremely low bits per pixel. While recent diffusion-based models provided enhanced generative performance at low bitrates, they often yields limited perceptual quality and prohibitive decoding latency due to multiple denoising steps. In this paper, we propose the single-step diffusion model for image compression that delivers high perceptual quality and fast decoding at ultra-low bitrates. Our approach incorporates two key innovations: (i) Vector-Quantized Residual (VQ-Residual) training, which factorizes a structural base code and a learned residual in latent space, capturing both global geometry and high-frequency details; and (ii) rate-aware noise modulation, which tunes denoising strength to match the desired bitrate. Extensive experiments show that ours achieves comparable compression performance to state-of-the-art methods while improving decoding speed by about 50x compared to prior diffusion-based methods, greatly enhancing the practicality of generative codecs.