Search Results for author: Chamara Saroj Weerasekera

Found 6 papers, 3 papers with code

DF-VO: What Should Be Learnt for Visual Odometry?

2 code implementations1 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.

Monocular Visual Odometry Optical Flow Estimation

Visual Odometry Revisited: What Should Be Learnt?

2 code implementations21 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.

Monocular Visual Odometry

Self-supervised Learning for Single View Depth and Surface Normal Estimation

no code implementations1 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.

Depth Prediction Monocular Depth Estimation +2

Just-in-Time Reconstruction: Inpainting Sparse Maps using Single View Depth Predictors as Priors

no code implementations11 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.

Depth Estimation Depth Prediction

Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction

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.

Depth And Camera Motion Depth Prediction +2

Learning Deeply Supervised Good Features to Match for Dense Monocular Reconstruction

no code implementations16 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.

Depth Estimation Monocular Reconstruction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.