# Single-step Diffusion for Image Compression at Ultra-Low Bitrates Source: [Single-step Diffusion for Image Compression at Ultra-Low Bitrates]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:41:29.127Z Authors: Chanung Park, Joo Chan Lee, Jong Hwan Ko Published: 2025-06-19T19:53:27.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Compression on Kodak (BD-Rate vs LPIPS/DISTS)](): Image Compression; Kodak; BD-Rate (DISTS): 207.11. ## Original sources and implementation [Original paper]() [PDF]()