用多阶段损失和合成数据提升单图反光去除效果
Utilizing Multi-step Loss for Single Image Reflection Removal
- 设计多阶段损失机制，增强模型对反光的建模能力
- 在SIR^2等数据集上超越现有模型，显著提升去反光效果
- 适合图像恢复、计算机视觉任务的开发者参考
图像反光去除对提升图像质量至关重要，能有效改善目标检测与图像分割等任务的表现。本文提出一种基于单张图像的反光去除新方法，不依赖特定网络结构，而是通过可泛化至图像到图像任务的新型训练策略实现。该策略体现在多阶段损失机制中，已在反光去除任务中验证其有效性。针对训练数据稀缺问题，我们利用Pix2Pix GAN构建了高质量、非线性的合成数据集RefGAN，显著提升模型学习反光模式的能力。此外，引入从环境图像深度估计中提取的范围深度图作为辅助特征，利用反射区域缺乏深度信息的特性。实验表明，该方法在SIR^2基准及多个真实场景数据集上均优于当前主流模型。
原文摘要 · Abstract (English)
Image reflection removal is crucial for restoring image quality. Distorted images can negatively impact tasks like object detection and image segmentation. In this paper, we present a novel approach for image reflection removal using a single image. Instead of focusing on model architecture, we introduce a new training technique that can be generalized to image-to-image problems, with input and output being similar in nature. This technique is embodied in our multi-step loss mechanism, which has proven effective in the reflection removal task. Additionally, we address the scarcity of reflection removal training data by synthesizing a high-quality, non-linear synthetic dataset called RefGAN using Pix2Pix GAN. This dataset significantly enhances the model's ability to learn better patterns for reflection removal. We also utilize a ranged depth map, extracted from the depth estimation of the ambient image, as an auxiliary feature, leveraging its property of lacking depth estimations for reflections. Our approach demonstrates superior performance on the SIR^2 benchmark and other real-world datasets, proving its effectiveness by outperforming other state-of-the-art models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。