Syn2Real Transfer Learning for Image Deraining using Gaussian Processes
This addresses the challenge of limited real-world labeled data for image deraining, offering a practical solution for computer vision applications, though it is incremental as it builds on existing semi-supervised and transfer learning approaches.
The paper tackles the problem of poor generalization of CNN-based image deraining methods from synthetic to real-world data by proposing a Gaussian Process-based semi-supervised learning framework, which achieves on-par performance with fully-labeled training using limited labeled data and superior results with unlabeled real-world images on datasets like Rain800 and Rain200H.
Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these methods are limited in the sense that they can be trained only on fully labeled data. Due to various challenges in obtaining real world fully-labeled image deraining datasets, existing methods are trained only on synthetically generated data and hence, generalize poorly to real-world images. The use of real-world data in training image deraining networks is relatively less explored in the literature. We propose a Gaussian Process-based semi-supervised learning framework which enables the network in learning to derain using synthetic dataset while generalizing better using unlabeled real-world images. Through extensive experiments and ablations on several challenging datasets (such as Rain800, Rain200H and DDN-SIRR), we show that the proposed method, when trained on limited labeled data, achieves on-par performance with fully-labeled training. Additionally, we demonstrate that using unlabeled real-world images in the proposed GP-based framework results in superior performance as compared to existing methods. Code is available at: https://github.com/rajeevyasarla/Syn2Real