学習型マルチスコピック融合による堅牢な深度推定
MFuseNet: Robust Depth Estimation with Learned Multiscopic Fusion
低コスト単眼カメラを水平・垂直に移動させて視差の揃った画像列を撮影し、複数のコストボリュームを学習ベースで融合して高精度な深度推定を実現した研究。
著者: Weihao Yuan, Rui Fan, Michael Yu Wang, Qifeng Chen
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
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.
