We design a multiscopic vision system that utilizes a low-cost monocular RGB camera to acquire accurate depth estimation. Unlike multi-view stereo with images captured at unconstrained camera poses, the proposed system controls the motion of a camera to capture a sequence of images in horizontally or vertically aligned positions with the same parallax. In this system, we propose a new heuristic method and a robust learning-based method to fuse multiple cost volumes between the reference image and its surrounding images. To obtain training data, we build a synthetic dataset with multiscopic images. The experiments on the real-world Middlebury dataset and real robot demonstration show that our multiscopic vision system outperforms traditional two-frame stereo matching methods in depth estimation. Our code and dataset are available at https://sites.google.com/view/multiscopic.
@article{arxiv.2108.02448,
title = {MFuseNet: Robust Depth Estimation with Learned Multiscopic Fusion},
author = {Weihao Yuan and Rui Fan and Michael Yu Wang and Qifeng Chen},
journal= {arXiv preprint arXiv:2108.02448},
year = {2021}
}
Comments
IEEE International Conference on Robotics and Automation (ICRA) + IEEE Robotics and Automation Letters (RA-L). arXiv admin note: substantial text overlap with arXiv:2001.08212