Results 11 to 20 of about 4,496,548 (308)
Depth Map Decomposition for Monocular Depth Estimation [PDF]
European Conference on Computer Vision, 2022 We propose a novel algorithm for monocular depth estimation that decomposes a metric depth map into a normalized depth map and scale features. The proposed network is composed of a shared encoder and three decoders, called G-Net, N-Net, and M-Net, which estimate gradient maps, a normalized depth map, and a metric depth map, respectively.
Jinyoung Jun +3 more
openaire +3 more sources
IEEE Access, 2017 Underwater optical cameras are widely used for security monitoring in ocean, such as earthquake prediction and tsunami alarming. Optical cameras recognize objects for autonomous underwater vehicles and provide security protection for sea-floor networks ...
Huimin Lu +7 more
doaj +2 more sources
Guided Depth Map Super-Resolution: A Survey [PDF]
ACM Computing Surveys, 2023 Guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution depth map from a low-resolution observation with the help of a paired high-resolution color image, is a longstanding and fundamental problem that has attracted ...
Zhiwei Zhong +4 more
semanticscholar +1 more source
Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells [PDF]
IEEE International Conference on Computer Vision, 2023 Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also ...
Xinyi Ye +5 more
semanticscholar +1 more source
Discrete Cosine Transform Network for Guided Depth Map Super-Resolution [PDF]
Computer Vision and Pattern Recognition, 2021 Guided depth super-resolution (GDSR) is an essential topic in multi-modal image processing, which reconstructs high-resolution (HR) depth maps from low-resolution ones collected with suboptimal conditions with the help of HR RGB images of the same scene.
Zixiang Zhao +4 more
semanticscholar +1 more source
BridgeNet: A Joint Learning Network of Depth Map Super-Resolution and Monocular Depth Estimation [PDF]
ACM Multimedia, 2021 Depth map super-resolution is a task with high practical application requirements in the industry. Existing color-guided depth map super-resolution methods usually necessitate an extra branch to extract high-frequency detail information from RGB image to
Q. Tang +6 more
semanticscholar +1 more source
RoutedFusion: Learning Real-Time Depth Map Fusion [PDF]
Computer Vision and Pattern Recognition, 2020 The efficient fusion of depth maps is a key part of most state-of-the-art 3D reconstruction methods. Besides requiring high accuracy, these depth fusion methods need to be scalable and real-time capable.
Silvan Weder +3 more
semanticscholar +1 more source
Channel Attention Based Iterative Residual Learning for Depth Map Super-Resolution [PDF]
Computer Vision and Pattern Recognition, 2020 Despite the remarkable progresses made in deep learning based depth map super-resolution (DSR), how to tackle real-world degradation in low-resolution (LR) depth maps remains a major challenge.
Xibin Song +6 more
semanticscholar +1 more source
HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation From a Single Depth Map [PDF]
Computer Vision and Pattern Recognition, 2020 3D hand shape and pose estimation from a single depth map is a new and challenging computer vision problem with many applications. The state-of-the-art methods directly regress 3D hand meshes from 2D depth images via 2D convolutional neural networks ...
J. Malik +7 more
semanticscholar +1 more source
Semi-Supervised Deep Learning for Monocular Depth Map Prediction [PDF]
Computer Vision and Pattern Recognition, 2017 Supervised deep learning often suffers from the lack of sufficient training data. Specifically in the context of monocular depth map prediction, it is barely possible to determine dense ground truth depth images in realistic dynamic outdoor environments.
Yevhen Kuznietsov +2 more
semanticscholar +1 more source