Zobrazeno 1 - 10
of 655
pro vyhledávání: '"Zeng, Yiming"'
Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant challenges to effec
Externí odkaz:
http://arxiv.org/abs/2403.01129
Object rearrangement, a fundamental challenge in robotics, demands versatile strategies to handle diverse objects, configurations, and functional needs. To achieve this, the AI robot needs to learn functional rearrangement priors in order to specify
Externí odkaz:
http://arxiv.org/abs/2312.01474
Publikováno v:
Proc. IEEE 43th Int. Conf. Distrib. Comput. Syst. (ICDCS),2023
Generating a long-distance quantum entanglement is one of the most essential functions of a quantum network to support quantum communication and computing applications. The successful entanglement rate during a probabilistic entanglement process decr
Externí odkaz:
http://arxiv.org/abs/2306.16671
Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called Flattening-Net
Externí odkaz:
http://arxiv.org/abs/2212.08892
Motivated by the intuition that the critical step of localizing a 2D image in the corresponding 3D point cloud is establishing 2D-3D correspondence between them, we propose the first feature-based dense correspondence framework for addressing the ima
Externí odkaz:
http://arxiv.org/abs/2207.05483
Publikováno v:
IEEE International Conference on Computer Communications 2022
Quantum networks are considered as a promising future platform for quantum information exchange and quantum applications, which have capabilities far beyond the traditional communication networks. Remote quantum entanglement is an essential component
Externí odkaz:
http://arxiv.org/abs/2205.15501
Publikováno v:
Zhongliu Fangzhi Yanjiu, Vol 51, Iss 1, Pp 55-60 (2024)
Objective To explore the effect and safety of magnetic resonance imaging and transrectal ultrasound (mpMRI-TRUS) image fusion targeted transperineal biopsy technique using electromagnetic needle tracking under local anesthesia. Methods We retrospecti
Externí odkaz:
https://doaj.org/article/beb8d0b37fb744cc96b406588d0f8bdb
We propose WarpingGAN, an effective and efficient 3D point cloud generation network. Unlike existing methods that generate point clouds by directly learning the mapping functions between latent codes and 3D shapes, Warping-GAN learns a unified local-
Externí odkaz:
http://arxiv.org/abs/2203.12917
This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation. We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) and further reason that temporal irregul
Externí odkaz:
http://arxiv.org/abs/2203.11590
Publikováno v:
IEEE Signal Processing Letters, vol. 29, pp. 1629-1633, 2022
One-bit compressive sensing is concerned with the accurate recovery of an underlying sparse signal of interest from its one-bit noisy measurements. The conventional signal recovery approaches for this problem are mainly developed based on the assumpt
Externí odkaz:
http://arxiv.org/abs/2203.11278