Zobrazeno 1 - 10
of 408
pro vyhledávání: '"Yang, Bisheng"'
In this paper, we explore a novel framework, EGIInet (Explicitly Guided Information Interaction Network), a model for View-guided Point cloud Completion (ViPC) task, which aims to restore a complete point cloud from a partial one with a single view i
Externí odkaz:
http://arxiv.org/abs/2407.02887
Automated Aerial Triangulation (AAT), aiming to restore image pose and reconstruct sparse points simultaneously, plays a pivotal role in earth observation. With its rich research heritage spanning several decades in photogrammetry, AAT has evolved in
Externí odkaz:
http://arxiv.org/abs/2402.01134
Autor:
Long, Chen, Zhang, Wenxiao, Chen, Zhe, Wang, Haiping, Liu, Yuan, Cao, Zhen, Dong, Zhen, Yang, Bisheng
We propose SparseDC, a model for Depth Completion of Sparse and non-uniform depth inputs. Unlike previous methods focusing on completing fixed distributions on benchmark datasets (e.g., NYU with 500 points, KITTI with 64 lines), SparseDC is specifica
Externí odkaz:
http://arxiv.org/abs/2312.00097
Autor:
Liao, Youqi, Kang, Shuhao, Li, Jianping, Liu, Yang, Liu, Yun, Dong, Zhen, Yang, Bisheng, Chen, Xieyuanli
Precise and rapid delineation of sharp boundaries and robust semantics is essential for numerous downstream robotic tasks, such as robot grasping and manipulation, real-time semantic mapping, and online sensor calibration performed on edge computing
Externí odkaz:
http://arxiv.org/abs/2311.12651
Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration. However, due to the modality difference between images and points, it is difficult to learn robust and discriminative cro
Externí odkaz:
http://arxiv.org/abs/2310.03420
Autor:
Kang, Shuhao, Liao, Youqi, Li, Jianping, Liang, Fuxun, Li, Yuhao, Zou, Xianghong, Li, Fangning, Chen, Xieyuanli, Dong, Zhen, Yang, Bisheng
Image-to-point cloud (I2P) registration is a fundamental task for robots and autonomous vehicles to achieve cross-modality data fusion and localization. Current I2P registration methods primarily focus on estimating correspondences at the point or pi
Externí odkaz:
http://arxiv.org/abs/2309.14660
In this paper, we present a new method for the multiview registration of point cloud. Previous multiview registration methods rely on exhaustive pairwise registration to construct a densely-connected pose graph and apply Iteratively Reweighted Least
Externí odkaz:
http://arxiv.org/abs/2304.00467
At present, the anchor-based or anchor-free models that use LiDAR point clouds for 3D object detection use the center assigner strategy to infer the 3D bounding boxes. However, in a real world scene, the LiDAR can only acquire a limited object surfac
Externí odkaz:
http://arxiv.org/abs/2202.11868
Autor:
Tu, Zhigang, Huang, Zhisheng, Chen, Yujin, Kang, Di, Bao, Linchao, Yang, Bisheng, Yuan, Junsong
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023
We present a method for reconstructing accurate and consistent 3D hands from a monocular video. We observe that detected 2D hand keypoints and the image texture provide important cues about the geometry and texture of the 3D hand, which can reduce or
Externí odkaz:
http://arxiv.org/abs/2201.09548
Autor:
Wu, Jiayu, Chen, Chi, Yan, Zhengfei, Wu, Shaolong, Wang, Zhiye, Li, Liuchun, Fu, Jing, Yang, Bisheng
Publikováno v:
In International Journal of Applied Earth Observation and Geoinformation September 2024 133