Frequency-Aware Perceptual Optimization for Low-Complexity Implicit Image Compression

We propose a frequency-aware perceptual optimization framework for low-complexity image compression, realized as a Realism-enhanced Region-based Implicit Codec (Re 2 IC). Re 2 IC models visual perception via saliency-guided region partitioning and local-global perceptual modulation. To enhance realism under complexity constraints, we introduce wavelet-Wasserstein distortion (WA-WD), a frequency-decomposed perceptual distortion that balances fidelity and realism through subband-aware modeling and provides a more reliable approximation than standard Wasserstein distortion. Together, these designs enable fine-grained spatial-spectral optimization, allowing Re 2 IC to achieve superior rate-perception trade-offs, outperforming generative codecs such as HiFiC while using less than 1% of their decoding cost. Extensive experiments demonstrate state-of-the-art perceptual performance among overfitted codecs. Beyond compression, WA-WD serves as a standalone, tunable perceptual metric with strong alignment to human preference (Pearson 94.6%, Spearman 92.3%) and competitive performance across multiple IQA benchmarks. Project page: https: //eedavidwu.github.io/ReReIC/ Frequency-Aware Perceptual Optimization for Low-Complexity Implicit Image Compression Re 2 IC HiFiC Original C3/WD: 0.230 bpp HiFiC: 0.231 bpp Re 2 IC: 0.224 bpp Original MLIC + + : 0.270 bpp VTM: 0.283 bpp Re 2 IC: 0.224 bpp