2 code implementations • 1 Mar 2021 • Huangying Zhan, Chamara Saroj Weerasekera, Jia-Wang Bian, Ravi Garg, Ian Reid
More surprisingly, they show that the well-trained networks enable scale-consistent predictions over long videos, while the accuracy is still inferior to traditional methods because of ignoring geometric information.
2 code implementations • 21 Sep 2019 • Huangying Zhan, Chamara Saroj Weerasekera, Jia-Wang Bian, Ian Reid
In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning.
no code implementations • 1 Mar 2019 • Huangying Zhan, Chamara Saroj Weerasekera, Ravi Garg, Ian Reid
In this work we present a self-supervised learning framework to simultaneously train two Convolutional Neural Networks (CNNs) to predict depth and surface normals from a single image.
Ranked #62 on Monocular Depth Estimation on KITTI Eigen split
no code implementations • 11 May 2018 • Chamara Saroj Weerasekera, Thanuja Dharmasiri, Ravi Garg, Tom Drummond, Ian Reid
Crucially, we obtain the confidence weights that parameterize the CRF model in a data-dependent manner via Convolutional Neural Networks (CNNs) which are trained to model the conditional depth error distributions given each source of input depth map and the associated RGB image.
1 code implementation • CVPR 2018 • Huangying Zhan, Ravi Garg, Chamara Saroj Weerasekera, Kejie Li, Harsh Agarwal, Ian Reid
Despite learning based methods showing promising results in single view depth estimation and visual odometry, most existing approaches treat the tasks in a supervised manner.
no code implementations • 16 Nov 2017 • Chamara Saroj Weerasekera, Ravi Garg, Yasir Latif, Ian Reid
Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images.