PaaF: Raising the perceived quality of INR-Based Image Compression
For researchers in image compression, PaaF advances INR-based methods by addressing encoding time and quality gaps, though improvements are incremental relative to established codecs.
PaaF introduces an INR-based image codec with improved architecture, adaptive quantization, and efficient entropy coding, achieving consistent gains in PSNR and perceptual quality over prior INR methods, narrowing the gap with traditional codecs.
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.