Abstract
Retinal fundus photography is indispensable for ophthalmic screening and diagnosis, yet image quality is often degraded by noise, artifacts, and uneven illumination. Recent GAN- and diffusion-based enhancement methods improve perceptual quality by aligning degraded images with high-quality distributions, but our analysis shows that this focus can distort intra-class geometry: clinically related samples become dispersed, disease-class boundaries blur, and downstream tasks such as grading or lesion detection are harmed. The Gromov Wasserstein (GW) discrepancy offers a principled solution by aligning distributions through internal pairwise distances, naturally preserving intra-class structure, but its high computational cost restricts practical use. To overcome this, we propose SGW-GAN, the first framework to incorporate Sliced GW (SGW) into retinal image enhancement. SGW approximates GW via random projections, retaining relational fidelity while greatly reducing cost. Experiments on public datasets show that SGW-GAN produces visually compelling enhancements, achieves superior diabetic retinopathy grading, and reports the lowest GW discrepancy across disease labels, demonstrating both efficiency and clinical fidelity for unpaired medical image enhancement.
Abstract (translated)
视网膜眼底摄影对于眼科筛查和诊断至关重要，然而图像质量常常因噪声、伪影及不均匀照明而受损。近年来基于生成对抗网络（GAN）和扩散模型的增强方法通过将退化图像与高质量分布对齐来提升感知质量，但我们的分析表明这种侧重会扭曲类内几何结构：临床相关的样本变得分散，疾病类别边界模糊，并且下游任务如分级或病变检测受到影响。Gromov-Wasserstein (GW) 差异提供了通过内部成对距离对齐分布的原理性解决方案，自然地保留了类内结构，但由于其高昂的计算成本，在实际应用中受到了限制。 为解决这一问题，我们提出了一种新的框架——SGW-GAN（Sliced Gromov-Wasserstein Generative Adversarial Network），首次将切片Gromov-Wasserstein (SGW) 融入视网膜图像增强。SGW 通过随机投影来近似 GW 差异，在大幅降低成本的同时保留了关系保真度。实验结果表明，SGW-GAN 在公共数据集上生成的视觉改进效果显著，糖尿病性视网膜病变分级表现优越，并且各类疾病标签之间的GW差异最小，从而展示了在未配对医学图像增强中同时具备高效性和临床精准性的能力。
URL
https://arxiv.org/abs/2601.13417
