RQUL-UIE: Revitalizing Quality-Unstable Labels for Underwater Image Enhancement via In-Dataset Self-Supervision
For researchers in underwater image enhancement, this method addresses the bottleneck of unstable label quality in paired datasets, offering a way to utilize low-quality labels without performance degradation.
This paper tackles the problem of unstable label quality in underwater image enhancement (UIE) datasets. The proposed diffusion-based self-supervised method achieves state-of-the-art restoration quality by exploiting label quality distribution and preventing low-quality labels from degrading model performance.
Underwater Image Enhancement (UIE) is essential for mitigating degradations caused by water medium. Although learning-based methods have advanced significantly, most rely on paired datasets with unstable label quality, which bottlenecks model performance. This paper proposes a diffusion-based, in-dataset self-supervised learning strategy designed to exploit the quality distribution of training labels. Specifically, we evaluate label quality via semantic perception embeddings from a pre-trained diffusion model in a training-free manner. These quality scores are subsequently quantized into noise-level indices, guiding a multi-step denoising process for level-wise supervision. This mechanism prevents low-quality labels from degrading the model while maximizing their utility during training. Furthermore, a Fourier-based refinement network is incorporated to explicitly reconstruct high-frequency components. Extensive evaluations demonstrate that our method consistently outperforms SOTA approaches in restoration quality. The code and pre-trained model will be available once accepted in link.