SPJFNet: Self-Mining Prior-Guided Joint Frequency Enhancement for Ultra-Efficient Dark Image Restoration

TL;DR

SPJFNet introduces a novel dark image restoration network that eliminates external priors, reduces computational complexity through frequency domain analysis, and achieves state-of-the-art performance with high efficiency.

Contribution

It proposes a self-mining guidance module and a dual-frequency framework to enhance efficiency and performance without relying on external priors.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Reduces model complexity and computational overhead.

Achieves faster inference with comparable or better restoration quality.

Abstract

Current dark image restoration methods suffer from severe efficiency bottlenecks, primarily stemming from: (1) computational burden and error correction costs associated with reliance on external priors (manual or cross-modal); (2) redundant operations in complex multi-stage enhancement pipelines; and (3) indiscriminate processing across frequency components in frequency-domain methods, leading to excessive global computational demands. To address these challenges, we propose an Efficient Self-Mining Prior-Guided Joint Frequency Enhancement Network (SPJFNet). Specifically, we first introduce a Self-Mining Guidance Module (SMGM) that generates lightweight endogenous guidance directly from the network, eliminating dependence on external priors and thereby bypassing error correction overhead while improving inference speed. Second, through meticulous analysis of different frequency domain characteristics, we reconstruct and compress multi-level operation chains into a single efficient operation via lossless wavelet decomposition and joint Fourier-based advantageous frequency enhancement, significantly reducing parameters. Building upon this foundation, we propose a Dual-Frequency Guidance Framework (DFGF) that strategically deploys specialized high/low frequency branches (wavelet-domain high-frequency enhancement and Fourier-domain low-frequency restoration), decoupling frequency processing to substantially reduce computational complexity. Rigorous evaluation across multiple benchmarks demonstrates that SPJFNet not only surpasses state-of-the-art performance but also achieves significant efficiency improvements, substantially reducing model complexity and computational overhead. Code is available at https://github.com/bywlzts/SPJFNet.