阴影特征细化网络：基于知识蒸馏的渐进式特征细化用于高效阴影去除
Shadow Feature Refinement Network: Progressive Feature Refinement based on Knowledge Distillation for Effective Shadow Removal
- Kyonggi University（庆熙大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出SFR-Net，结合监督学习、特征细化损失与知识蒸馏，并引入后处理算法，在ISTD+和SRD数据集上实现高效且自然的阴影去除。
AI中文摘要：
在深度学习领域已取得显著进展；然而，由于受光照条件影响的阴影大小和颜色多变，阴影去除仍然是一个持续的挑战。本研究提出了一种新颖的阴影特征细化网络（SFR-Net），该网络利用监督学习、特征细化损失和知识蒸馏来提升阴影去除性能。进一步引入了一种专门的后处理算法，以恢复生成的去阴影图像中的自然色彩一致性。我们在两个公开数据集上评估了我们的方法：调整图像阴影三元组数据集（ISTD+）和阴影去除数据集（SRD），这些数据集展示了在多样条件下的强大泛化能力。在ISTD+上，我们的模型在整个图像上实现了均方根误差（RMSE）为3.4627，结构相似性指数（SSIM）为0.9382。在SRD上，它记录了RMSE为4.3781和SSIM为0.9341。这些全面的结果表明，我们的方法在阴影和非阴影区域均表现出竞争力，同时为稳健且感知自然的阴影去除设定了有前景的方向。代码可在以下网址获取：此https URL。
英文摘要：
In the field of deep learning, has seen significant advancements; however, shadow removal remains a persistent challenge owing to the variable sizes and colors of shadows influenced by lighting conditions. This study proposes a novel shadow feature refinement network (SFR-Net), which leverages supervised learning, feature refinement loss, and knowledge distillation to enhance shadow removal performance. A dedicated post-processing algorithm is further introduced to restore natural color consistency in the generated shadow-free images. We evaluated our method on two public datasets: the adjusted image shadow triplet dataset (ISTD+) and the shadow removal dataset (SRD), which demonstrate strong generalization capabilities under diverse conditions. On ISTD+, our model achieved a root mean square error (RMSE) of 3.4627 and structural similarity index measure (SSIM) of 0.9382 across the entire image. On SRD, it recorded an RMSE of 4.3781 and an SSIM of 0.9341. These comprehensive results show that our approach performs competitively across both shadow and non-shadow regions while setting a promising direction for robust and perceptually natural shadow removal. Code is available at https://github.com/DongHyun99/SFRNet.
