Spline Human Motion Recovery

Deep learning has achieved remarkable progress in computer vision and image analysis. However, raindrop removal from a single image still remains challenging, due to a wide range of raindrop diversities (e.g., shapes and sizes) and various surface reflections. in this paper, we propose an iterative neural network with feedback strategy and contrastive learning for single image raindrop removal. First, we design an iterative feedback neural network to refine low-level representations with high-level information, i.e., the output of the previous iteration is used as input for the next iteration, together with the input image with raindrops. As a result, raindrops could be gradually removed through this feedback manner. Then, we deploy contrastive regularization to push the restored image from each iteration close to the clean images without raindrops, but away from rainy images with raindrops. The positive pairs used in contrastive regularization are formed by restored images and clean ones, while the negative pairs are formed by restored images and rainy ones. Extensive experiments on two raindrop benchmark datasets demonstrate the effectiveness of the proposed approach in comparison with the state-of-the-art methods.