Vox-fusion: Dense tracking and map** with voxel-based neural implicit representation

X Yang, H Li, H Zhai, Y Ming, Y Liu… - 2022 IEEE International …, 2022 - ieeexplore.ieee.org
In this work, we present a dense tracking and map** system named Vox-Fusion, which
seamlessly fuses neural implicit representations with traditional volumetric fusion methods …

Unsupervised learning of monocular depth estimation and visual odometry with deep feature reconstruction

H Zhan, R Garg, CS Weerasekera… - Proceedings of the …, 2018 - openaccess.thecvf.com
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 …

Defeat-net: General monocular depth via simultaneous unsupervised representation learning

J Spencer, R Bowden… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
In the current monocular depth research, the dominant approach is to employ unsupervised
training on large datasets, driven by warped photometric consistency. Such approaches lack …

Deconstructing self-supervised monocular reconstruction: The design decisions that matter

J Spencer, C Russell, S Hadfield, R Bowden - ar** with convolutional neural networks
H Zhou, B Ummenhofer, T Brox - International Journal of Computer Vision, 2020 - Springer
We present a system for dense keyframe-based camera tracking and depth map estimation
that is entirely learned. For tracking, we estimate small pose increments between the current …

Learning meshes for dense visual SLAM

M Bloesch, T Laidlow, R Clark… - Proceedings of the …, 2019 - openaccess.thecvf.com
Estimating motion and surrounding geometry of a moving camera remains a challenging
inference problem. From an information theoretic point of view, estimates should get better …

Camera relocalization by exploiting multi-view constraints for scene coordinates regression

M Cai, H Zhan… - Proceedings of the …, 2019 - openaccess.thecvf.com
We propose a method for learning a scene coordinate regression model to perform accurate
camera relocalization in a known environment from a single RGB image. Our method …

Semi-dense stereo matching using dual CNNs

W Mao, M Wang, J Zhou, M Gong - 2019 IEEE Winter …, 2019 - ieeexplore.ieee.org
A robust solution for semi-dense stereo matching is presented. It utilizes two CNN models for
computing stereo matching cost and performing confidence-based filtering, respectively …

Combining deep learning and RGBD SLAM for monocular indoor autonomous flight

J Martínez-Carranza, LO Rojas-Perez… - … Conference on Artificial …, 2018 - Springer
We present a system that uses deep learning and visual SLAM for autonomous flight in
indoor environments. In this spirit, we use a state-of-the-art CNN architecture to obtain depth …

A Study on the Effects of Binaural Listening Materials on Second Language Listening Comprehension

S Ji, K Li - 2018 International Joint Conference on Information …, 2018 - ieeexplore.ieee.org
The purpose of this study was to investigate the effects of the listening material, which was
field recorded and made for mono and binaural listening materials based on Ambisonics …