eess.IV · 2606.00158 Copy arXiv ID · May 29, 2026 Save Training-Free Continuous Bitrate Control for Scalable Image Coding for Humans and Machines Authors: Yui Tatsumi , Hiroshi Watanabe
Organizations: Graduate School of FSE, Waseda University Tokyo, Japan
Abstract Continuous variable-rate compression is highly demanded in real-world applications, but remains underexplored in scalable image coding for humans and machines. In this paper, we propose a training-free variable-rate scalable image coding framework. By adaptively adjusting quantization step sizes based on predicted scale values, the proposed method enables independent and continuous bitrate control for the machine and enhancement layers while preserving important latent information in each layer. Experimental results demonstrate the effectiveness of the proposed method and highlight the importance of bitrate allocation between the two layers.
Explore similar work Jul 15, 2026 · Calvin-Khang Ta, Praneet Singh, Tong Shao +1 Learned Image Compression Ultra-Low Bitrates
May 22, 2026 · Hao Cao, Wenqi Guo, Zhijin Qin +1 Learned Image Compression Entropy Coding
May 6, 2026 · Kedar Tatwawadi, Parisa Rahimzadeh, Zhanghao Sun +5 Learned Image Compression Ultra-Low Bitrates
Jul 15, 2026 · cs.CV J/K move · Enter open · S save
Calvin-Khang Ta, Praneet Singh, Tong Shao, Peng Yin
Dolby Laboratories, USA
Learned image compression (LIC) is bottlenecked by the need to store independent models for each rate-distortion operating point. Existing variable bit-rate (VBR) methods aim to reduce this overhead via dense parameter modulation, but forcing a shared backbone to approximate divergent mappings causes severe feature entanglement. Specifically, low-rate smoothing gradients inherently conflict with the preservation of high-frequency textural details, leading to sub-optimal performance. To resolve this, we propose MixCompress, a unified VBR framework based on sparse structural specialization. While sparsely gated Mixture-of-Experts (MoE) routing successfully mitigates gradient conflict, it operates on a fixed computational budget. To address the increased representational demands of higher bit-rates we introduce a Mixture-of-Depths (MoD) extension to dynamically scale model capacity. Combined with Conditional Auxiliary Transforms (CAT) for dynamic sub-band energy modulation, our hierarchical framework effectively dynamically scales capacity. Extensive evaluations demonstrate that MixCompress not only matches individually optimized single-rate baselines but can even surpass them, establishing a new Pareto frontier for computationally efficient image coding.