DeepHQ: Learned Hierarchical Quantizer for Progressive Deep Image Coding
Open Access
- 12 January 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (1) , 1-24
Abstract
Research on entropy model-based Learned Image Compression (LIC) has been actively progressing, leading to rapid advancements in coding efficiency. Beyond improvements in coding efficiency, LIC methods have also been explored for practical codec development. Despite these advancements, research on learned Progressive Image Coding (PIC) remains in its early stages. PIC aims to encode multiple quality levels into a single bitstream, improving bitstream versatility and achieving higher compression efficiency than simulcast compression. Existing learned PIC methods hierarchically quantize transformed latent representations with varying quantization step sizes. More specifically, these approaches progressively compress the additional information needed for quality improvement, considering that a wider quantization interval for lower-quality compression includes multiple narrower subintervals for higher-quality compression. However, they rely on handcrafted quantization hierarchies, leading to suboptimal compression efficiency. In this article, we propose a learned PIC method that first exploits learned quantization step sizes for each quantization layer. We also incorporate selective compression, ensuring that only essential representation components are retained in each quantization layer. Our experimental results demonstrate that the proposed method significantly enhances coding efficiency compared to the existing approaches while also reducing decoding time and model size. The source code is publicly available at https://github.com/JooyoungLeeETRI/DeepHQ .Keywords
All Related Versions
Funding Information
- Electronics and Telecommunications Research Institute (25YC1100)
This publication has 17 references indexed in Scilit:
- Efficient Contextformer: Spatio-Channel Window Attention for Fast Context Modeling in Learned Image CompressionIEEE Transactions on Circuits and Systems for Video Technology, 2024
- Learned Progressive Image Compression With Dead-Zone QuantizersIEEE Transactions on Circuits and Systems for Video Technology, 2022
- ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding2022
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- Learning Context-Based Nonlocal Entropy Modeling for Image CompressionIEEE Transactions on Neural Networks and Learning Systems, 2021
- Checkerboard Context Model for Efficient Learned Image Compression2021
- End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context ModelingIEEE Transactions on Image Processing, 2021
- Efficient and Effective Context-Based Convolutional Entropy Modeling for Image CompressionIEEE Transactions on Image Processing, 2020
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Full Resolution Image Compression with Recurrent Neural Networks2017