Abstract
Given a pair of rectified images, the goal of stereo matching is to estimate the disparity. We aim at building an efficient network so we exploit the architecture of DispNetC and propose EDNet, a network that takes advantage of both the concatenation cost volume and the correlation volume by forming a combination volume. We further propose the attention-based residual learning module by embedding spatial attention module. Experimental results show that our model outperforms previous state-of-the-art methods on Scene Flow and KITTI datasets while runs significantly faster, demonstrating the effectiveness of our proposed method.
Abstract (translated)
URL
https://arxiv.org/abs/2010.13338
