Results 51 to 60 of about 6,226 (231)

Monocular Depth Estimation Based on Multi-Scale Graph Convolution Networks

IEEE Access, 2020
Monocular depth estimation is a foundation task of three-dimensional (3D) reconstruction which is used to improve the accuracy of environment perception. Because of the simpler hardware requirement, it is more suitable than other multi-view methods.
Junwei Fu, Jun Liang, Ziyang Wang
doaj   +1 more source

Bidirectional Attention Network for Monocular Depth Estimation [PDF]

2021 IEEE International Conference on Robotics and Automation (ICRA), 2021
In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integrating local and global information in convolutional neural networks.
Shubhra Aich, Jean Marie Uwabeza Vianney, Md. Amirul Islam, Mannat Kaur, Bingbing Liu   +4 more
openaire   +2 more sources

Encoder-Decoder Structure with Multiscale Receptive Field Block for Unsupervised Depth Estimation from Monocular Video

Remote Sensing, 2022
Monocular depth estimation is a fundamental yet challenging task in computer vision as depth information will be lost when 3D scenes are mapped to 2D images.
Songnan Chen, Junyu Han, Mengxia Tang, Ruifang Dong, Jiangming Kan   +4 more
doaj   +1 more source

Adversarial Attacks on Monocular Depth Estimation

CoRR, 2020
Recent advances of deep learning have brought exceptional performance on many computer vision tasks such as semantic segmentation and depth estimation. However, the vulnerability of deep neural networks towards adversarial examples have caused grave concerns for real-world deployment.
Ziqi Zhang, Xinge Zhu, Yingwei Li, Xiangqun Chen, Yao Guo 0001   +4 more
openaire   +2 more sources

LUMDE: Light-Weight Unsupervised Monocular Depth Estimation via Knowledge Distillation

Applied Sciences, 2022
The use of the unsupervised monocular depth estimation network approach has seen rapid progress in recent years, as it avoids the use of ground truth data, and also because monocular cameras are readily available in most autonomous devices. Although some
Wenze Hu, Xue Dong, Ning Liu, Yuanfeng Chen   +3 more
doaj   +1 more source

Depth-Relative Self Attention for Monocular Depth Estimation

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023
Monocular depth estimation is very challenging because clues to the exact depth are incomplete in a single RGB image. To overcome the limitation, deep neural networks rely on various visual hints such as size, shade, and texture extracted from RGB information. However, we observe that if such hints are overly exploited, the network can be biased on RGB
Kyuhong Shim, Jiyoung Kim, Gusang Lee, Byonghyo Shim   +3 more
openaire   +2 more sources

Learning Depth for Scene Reconstruction Using an Encoder-Decoder Model

IEEE Access, 2020
Depth estimation has received considerable attention and is often applied to visual simultaneous localization and mapping (SLAM) for scene reconstruction.
Xiaohan Tu, Cheng Xu, Siping Liu, Guoqi Xie, Jing Huang, Renfa Li, Junsong Yuan   +6 more
doaj   +1 more source

Monocular Depth Estimation Based on Multi-Scale Depth Map Fusion

IEEE Access, 2021
Monocular depth estimation is a basic task in machine vision. In recent years, the performance of monocular depth estimation has been greatly improved. However, most depth estimation networks are based on a very deep network to extract features that lead
Xin Yang, Qingling Chang, Xinglin Liu, Siyuan He, Yan Cui   +4 more
doaj   +1 more source

EdgeConv with Attention Module for Monocular Depth Estimation [PDF]

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022
Monocular depth estimation is an especially important task in robotics and autonomous driving, where 3D structural information is essential. However, extreme lighting conditions and complex surface objects make it difficult to predict depth in a single image.
Minhyeok Lee, Sangwon Hwang, Chaewon Park, Sangyoun Lee   +3 more
openaire   +2 more sources

DeepFusion encoder for unsupervised monocular metric depth estimation [PDF]

PeerJ Computer Science
Monocular depth estimation is a fundamental task in computer vision, with significant applications in autonomous driving and robotics. However, accurately estimating depth from a single image remains challenging due to the absence of direct depth cues ...
Zhiwei Huang, Mohammed A. H. Ali, Yusoff Nukman, Shikai Zhang, Hui Chen, Mohammad Alkhedher, Hai lu Xu   +6 more
doaj   +2 more sources