Windowed Bundle Adjustment Framework for Unsupervised Learning of Monocular Depth Estimation With U-Net Extension and Clip Loss

2020 ◽  
Vol 5 (2) ◽  
pp. 3283-3290 ◽  
Author(s):  
Lipu Zhou ◽  
Michael Kaess
Keyword(s):  
Unsupervised Learning ◽  
Depth Estimation ◽  
Bundle Adjustment ◽  
Monocular Depth

scholarly journals An Adaptive Unsupervised Learning Framework for Monocular Depth Estimation

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 148142-148151
Author(s):  
Delong Yang ◽  
Xunyu Zhong ◽  
Lixiong Lin ◽  
Xiafu Peng
Keyword(s):  
Unsupervised Learning ◽  
Depth Estimation ◽  
Learning Framework ◽  
Monocular Depth

Monocular depth estimation based on unsupervised learning

2019 ◽  
Author(s):  
Wan Liu ◽  
Yan Sun ◽  
XuCheng Wang ◽  
Lin Yang ◽  
Zhenrong Zheng
Keyword(s):  
Unsupervised Learning ◽  
Depth Estimation ◽  
Monocular Depth

scholarly journals Occlusion-Aware Unsupervised Learning of Monocular Depth, Optical Flow and Camera Pose with Geometric Constraints

2018 ◽  
Vol 10 (10) ◽  
pp. 92 ◽  
Author(s):  
Qianru Teng ◽  
Yimin Chen ◽  
Chen Huang
Keyword(s):  
Optical Flow ◽  
Empirical Evaluation ◽  
Depth Estimation ◽  
Bundle Adjustment ◽  
Geometric Constraints ◽  
Camera Motion ◽  
Low Level ◽  
Unsupervised Neural Network ◽  
Consistency Constraints ◽  
Monocular Depth

We present an occlusion-aware unsupervised neural network for jointly learning three low-level vision tasks from monocular videos: depth, optical flow, and camera motion. The system consists of three different predicting sub-networks simultaneously coupled by combined loss terms and is capable of computing each task independently on test samples. Geometric constraints extracted from scene geometry which have traditionally been used in bundle adjustment or pose-graph optimization are formed as various self-supervisory signals during our end-to-end learning approach. Different from prior works, our image reconstruction loss also takes account of optical flow. Moreover, we impose novel 3D flow consistency constraints over the predictions of all the three tasks. By explicitly modeling occlusion and taking utilization of both 2D and 3D geometry relationships, abundant geometric constraints are formed over estimated outputs, enabling the system to capture both low-level representations and high-level cues to infer thinner scene structures. Empirical evaluation on the KITTI dataset demonstrates the effectiveness and improvement of our approach: (1) monocular depth estimation outperforms state-of-the-art unsupervised methods and is comparable to stereo supervised ones; (2) optical flow prediction ranks top among prior works and even beats supervised and traditional ones especially in non-occluded regions; (3) pose estimation outperforms established SLAM systems under comparable input settings with a reasonable margin.

Unsupervised Monocular Depth Estimation for Autonomous Driving

2019 ◽  
pp. 128
Author(s):  
Chih-Shuan Huang ◽  
Wan-Nung Tsung ◽  
Wei-Jong Yang ◽  
Chin-Hsing Chen
Keyword(s):  
Depth Estimation ◽  
Autonomous Driving ◽  
Monocular Depth

scholarly journals Unsupervised Learning-Based Depth Estimation-Aided Visual SLAM Approach

2019 ◽  
Vol 39 (2) ◽  
pp. 543-570 ◽  
Author(s):  
Mingyang Geng ◽  
Suning Shang ◽  
Bo Ding ◽  
Huaimin Wang ◽  
Pengfei Zhang
Keyword(s):  
Unsupervised Learning ◽  
Depth Estimation ◽  
Visual Slam

Hierarchical Object Relationship Constrained Monocular Depth Estimation.

2021 ◽  
pp. 108116
Author(s):  
Shuai Li ◽  
Jiaying Shi ◽  
Wenfeng Song ◽  
Aimin Hao ◽  
Hong Qin
Keyword(s):  
Depth Estimation ◽  
Monocular Depth ◽  
Object Relationship
Sign in / Sign up

Export Citation Format

Share Document