Zobrazeno 1 - 10
of 408
pro vyhledávání: '"Zha, Hongbin"'
Simultaneous localization and mapping (SLAM) with implicit neural representations has received extensive attention due to the expressive representation power and the innovative paradigm of continual learning. However, deploying such a system within a
Externí odkaz:
http://arxiv.org/abs/2407.13338
Visual-inertial odometry (VIO) has demonstrated remarkable success due to its low-cost and complementary sensors. However, existing VIO methods lack the generalization ability to adjust to different environments and sensor attributes. In this paper,
Externí odkaz:
http://arxiv.org/abs/2405.16754
We introduce a novel depth estimation technique for multi-frame structured light setups using neural implicit representations of 3D space. Our approach employs a neural signed distance field (SDF), trained through self-supervised differentiable rende
Externí odkaz:
http://arxiv.org/abs/2405.12006
In recent years, deep neural networks have shown remarkable progress in dense disparity estimation from dynamic scenes in monocular structured light systems. However, their performance significantly drops when applied in unseen environments. To addre
Externí odkaz:
http://arxiv.org/abs/2310.08934
Publikováno v:
IEEE Robotics and Automation Letters ( Volume: 7, Issue: 2, April 2022). pp 5111 - 5118
We introduced Temporally Incremental Disparity Estimation Network (TIDE-Net), a learning-based technique for disparity computation in mono-camera structured light systems. In our hardware setting, a static pattern is projected onto a dynamic scene an
Externí odkaz:
http://arxiv.org/abs/2310.08932
We address the problem of active mapping with a continually-learned neural scene representation, namely Active Neural Mapping. The key lies in actively finding the target space to be explored with efficient agent movement, thus minimizing the map unc
Externí odkaz:
http://arxiv.org/abs/2308.16246
Autor:
Xu, Shaocong, Chen, Xiaoxue, Zheng, Yuhang, Zhou, Guyue, Chen, Yurong, Zha, Hongbin, Zhao, Hao
In this study, we tackle the challenging fine-grained edge detection task, which refers to predicting specific edges caused by reflectance, illumination, normal, and depth changes, respectively. Prior methods exploit multi-scale convolutional network
Externí odkaz:
http://arxiv.org/abs/2308.03092
Autor:
Gao, Huan-ang, Tian, Beiwen, Li, Pengfei, Chen, Xiaoxue, Zhao, Hao, Zhou, Guyue, Chen, Yurong, Zha, Hongbin
Room layout estimation is a long-existing robotic vision task that benefits both environment sensing and motion planning. However, layout estimation using point clouds (PCs) still suffers from data scarcity due to annotation difficulty. As such, we a
Externí odkaz:
http://arxiv.org/abs/2301.13865
Visual re-localization aims to recover camera poses in a known environment, which is vital for applications like robotics or augmented reality. Feed-forward absolute camera pose regression methods directly output poses by a network, but suffer from l
Externí odkaz:
http://arxiv.org/abs/2210.12748