Multi-Scale Gradient Image Super-Resolution for Preserving SIFT Key Points in Low-Resolution Images

摘要

Low-resolution images present challenges to a variety of object recognition problems in a variety of surveillance and navigation applications. In recent years, deep learning has advanced the state of the art in image super-resolution (SR) in terms of pixel domain peak signal to noise ratio (PSNR)/ mean square error (MSE). Inspired by the recent advances of deep convolutional neural networks in general image SR tasks, we develop a computer vision task-driven image SR solution by learning super-resolved gradient images using multiple convolutional neural networks for different scales. Recovering super-resolved gradient images at multiple scales, enables the system to recover more information useful for high level vision tasks than simply SR in the pixel domain. In particular, we propose a residual learning framework to perform image SR in the Difference of Gaussian (DOG) domain. The trained residual network models are then adapted to drive a widely adopted key point algorithm for image recognition, i.e. the SIFT detection and matching. Experimental results show that the proposed approach can significantly improve the SIFT keypoints repeatability compared to the state of the art in pixel domain image SR solutions.