PaaF: Raising the perceived quality of INR-Based Image Compression

2026-06-19

AI Summary

This work addresses the limitations of existing implicit neural representation (INR)-based image compression methods, which often suffer from low encoding efficiency and suboptimal rate-distortion performance. To overcome these challenges, we propose PaaF (Picture as a Function), a novel codec that, within a purely INR-based framework, systematically integrates adaptive quantization and efficient entropy coding for the first time. We further introduce an improved network architecture that preserves the inherent parallelism of INR decoding while significantly enhancing compression efficiency. Experimental results demonstrate that PaaF outperforms current INR-based approaches in both objective metrics such as PSNR and perceptual quality, effectively narrowing the performance gap with state-of-the-art conventional compression techniques.

Abstract

Implicit Neural Representations (INRs) have recently emerged as a promising paradigm for image compression, offering a fundamentally different approach from traditional and learned codecs. Nevertheless, INR-based methods for image compression suffer from long encoding times and a consistent performance gap in classic quality metrics such as PSNR. In this work, we explore the potential of purely INR-based compression methods and we propose PaaF (Picture as a Function), a novel INR-based image codec that introduces improved architectural design, adaptive quantization, and an efficient entropy coding scheme. These components are designed to enhance rate-distortion performance while preserving the simplicity and parallelizability of INR-based decoding. Experimental results demonstrate consistent improvements over existing INR-based methods in both quantitative metrics and perceptual quality. These findings highlight the potential of INR-based approaches and contribute to narrowing the gap between functional representations and more established compression paradigms.

Problem

• Implicit Neural Representations
• Image Compression
• Perceived Quality
• Rate-Distortion Performance
• Encoding Time

Innovation

• Implicit Neural Representations
• Image Compression
• Adaptive Quantization
• Entropy Coding
• Perceptual Quality