Zobrazeno 1 - 10
of 286
pro vyhledávání: '"Thomas, Diego"'
3D-shape reconstruction in extreme environments, such as low illumination or scattering condition, has been an open problem and intensively researched. Active stereo is one of potential solution for such environments for its robustness and high accur
Externí odkaz:
http://arxiv.org/abs/2410.15376
Active 3D measurement, especially structured light (SL) has been widely used in various fields for its robustness against textureless or equivalent surfaces by low light illumination. In addition, reconstruction of large scenes by moving the SL syste
Externí odkaz:
http://arxiv.org/abs/2410.15378
Volumetric shape representations have become ubiquitous in multi-view reconstruction tasks. They often build on regular voxel grids as discrete representations of 3D shape functions, such as SDF or radiance fields, either as the full shape model or a
Externí odkaz:
http://arxiv.org/abs/2407.19837
Autor:
Teshima, Hitoshi, Wake, Naoki, Thomas, Diego, Nakashima, Yuta, Kawasaki, Hiroshi, Ikeuchi, Katsushi
Recent increase of remote-work, online meeting and tele-operation task makes people find that gesture for avatars and communication robots is more important than we have thought. It is one of the key factors to achieve smooth and natural communicatio
Externí odkaz:
http://arxiv.org/abs/2309.16162
We unveil how generalizable AI can be used to improve multi-view 3D pedestrian detection in unlabeled target scenes. One way to increase generalization to new scenes is to automatically label target data, which can then be used for training a detecto
Externí odkaz:
http://arxiv.org/abs/2308.04515
Autor:
Teshima, Hitoshi, Wake, Naoki, Thomas, Diego, Nakashima, Yuta, Kawasaki, Hiroshi, Ikeuchi, Katsushi
Body language such as conversational gesture is a powerful way to ease communication. Conversational gestures do not only make a speech more lively but also contain semantic meaning that helps to stress important information in the discussion. In the
Externí odkaz:
http://arxiv.org/abs/2210.06790
Publikováno v:
In Computers & Graphics November 2024 124
Publikováno v:
In Automation in Construction November 2024 167
We propose a new 2D pose refinement network that learns to predict the human bias in the estimated 2D pose. There are biases in 2D pose estimations that are due to differences between annotations of 2D joint locations based on annotators' perception
Externí odkaz:
http://arxiv.org/abs/2107.03000
Autor:
Thomas, Diego
We propose a method to build in real-time animated 3D head models using a consumer-grade RGB-D camera. Our proposed method is the first one to provide simultaneously comprehensive facial motion tracking and a detailed 3D model of the user's head. Any
Externí odkaz:
http://arxiv.org/abs/2004.10557