Syn2Real Transfer Learning for Image Deraining Using Gaussian Processes
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2723-2733
Abstract
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, Rain100H 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.Keywords
This publication has 39 references indexed in Scilit:
- Removing Rain from a Single Image via Discriminative Sparse Coding2015
- Utilizing Local Phase Information to Remove Rain from VideoInternational Journal of Computer Vision, 2014
- A Generalized Low-Rank Appearance Model for Spatio-temporally Correlated Rain Streaks2013
- Restoring an Image Taken through a Window Covered with Dirt or Rain2013
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Vision and RainInternational Journal of Computer Vision, 2007
- Rain Removal in Video by Combining Temporal and Chromatic Properties2006
- UCID: an uncompressed color image database2003
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000