Zobrazeno 1 - 10
of 139
pro vyhledávání: '"Mordohai, P."'
Autor:
Wang, Weihan, Chou, Chieh, Sevagamoorthy, Ganesh, Chen, Kevin, Chen, Zheng, Feng, Ziyue, Xia, Youjie, Cai, Feiyang, Xu, Yi, Mordohai, Philippos
We propose an accurate and robust initialization approach for stereo visual-inertial SLAM systems. Unlike the current state-of-the-art method, which heavily relies on the accuracy of a pure visual SLAM system to estimate inertial variables without up
Externí odkaz:
http://arxiv.org/abs/2403.07225
We introduce a learning-based depth map fusion framework that accepts a set of depth and confidence maps generated by a Multi-View Stereo (MVS) algorithm as input and improves them. This is accomplished by integrating volumetric visibility constraint
Externí odkaz:
http://arxiv.org/abs/2308.08715
Visual-inertial initialization can be classified into joint and disjoint approaches. Joint approaches tackle both the visual and the inertial parameters together by aligning observations from feature-bearing points based on IMU integration then use a
Externí odkaz:
http://arxiv.org/abs/2308.02670
Autor:
Wang, Weihan, Joshi, Bharat, Burgdorfer, Nathaniel, Batsos, Konstantinos, Li, Alberto Quattrini, Mordohai, Philippos, Rekleitis, Ioannis
This paper addresses real-time dense 3D reconstruction for a resource-constrained Autonomous Underwater Vehicle (AUV). Underwater vision-guided operations are among the most challenging as they combine 3D motion in the presence of external forces, li
Externí odkaz:
http://arxiv.org/abs/2304.02704
We present a new loss function for joint disparity and uncertainty estimation in deep stereo matching. Our work is motivated by the need for precise uncertainty estimates and the observation that multi-task learning often leads to improved performanc
Externí odkaz:
http://arxiv.org/abs/2304.00152
We address the problem of estimating the shape of a person's head, defined as the geometry of the complete head surface, from a video taken with a single moving camera, and determining the alignment of the fitted 3D head for all video frames, irrespe
Externí odkaz:
http://arxiv.org/abs/2109.02740
Autor:
Cai, Changjiang, Mordohai, Philippos
Deep networks for stereo matching typically leverage 2D or 3D convolutional encoder-decoder architectures to aggregate cost and regularize the cost volume for accurate disparity estimation. Due to content-insensitive convolutions and down-sampling an
Externí odkaz:
http://arxiv.org/abs/2010.07350
End-to-end deep networks represent the state of the art for stereo matching. While excelling on images framing environments similar to the training set, major drops in accuracy occur in unseen domains (e.g., when moving from synthetic to real scenes)
Externí odkaz:
http://arxiv.org/abs/2010.07347
Stereo matching is one of the longest-standing problems in computer vision with close to 40 years of studies and research. Throughout the years the paradigm has shifted from local, pixel-level decision to various forms of discrete and continuous opti
Externí odkaz:
http://arxiv.org/abs/2004.08566
Autor:
Sun, Bo, Mordohai, Philippos
Plane detection in 3D point clouds is a crucial pre-processing step for applications such as point cloud segmentation, semantic mapping and SLAM. In contrast to many recent plane detection methods that are only applicable on organized point clouds, o
Externí odkaz:
http://arxiv.org/abs/1905.02553