Efficient Progressive Image Compression with Variance-aware Masking

2024-11-15

arXiv.org

AI Summary

To address the challenge of simultaneously achieving fine-grained quality control and perceptual fidelity in progressive image compression, this paper proposes a parameter-free variance-aware progressive coding framework. Methodologically: (1) it introduces a dual latent representation—base + residual—augmented with hyperprior modeling to improve entropy estimation accuracy; (2) it designs a parameter-free variance-aware masking mechanism that performs adaptive importance ranking and block-wise transmission based on element-wise variance of latent variables; and (3) it incorporates a Rate Enhancement Module (REM) to dynamically refine entropy model parameters. The framework enables arbitrary intermediate-quality reconstruction, significantly reducing decoding latency (↓38%), computational complexity (↓42%), and model parameter count (↓51%). It achieves state-of-the-art rate-distortion performance across multiple benchmarks.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Machine Learning: Learning on the Edge & Model Compression
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compression method in which an image is first represented as a pair of base-quality and top-quality latent representations. Next, a residual latent representation is encoded as the element-wise difference between the top and base representations. Our scheme enables progressive image compression with element-wise granularity by introducing a masking system that ranks each element of the residual latent representation from most to least important, dividing it into complementary components, which can be transmitted separately to the decoder in order to obtain different reconstruction quality. The masking system does not add further parameters nor complexity. At the receiver, any elements of the top latent representation excluded from the transmitted components can be independently replaced with the mean predicted by the hyperprior architecture, ensuring reliable reconstructions at any intermediate quality level. We also introduced Rate Enhancement Modules (REMs), which refine the estimation of entropy parameters using already decoded components. We obtain results competitive with state-of-the-art competitors, while significantly reducing computational complexity, decoding time, and number of parameters.

Problem

• Image compression
• Perceptual detail preservation
• Variable clarity transmission

Innovation

• Progressive Image Compression
• Perceptual Detail Preservation
• Rate Enhancement Module