Zobrazeno 1 - 10
of 281
pro vyhledávání: '"Huang, Junwen"'
Autor:
Vutukur, Shishir Reddy, Haugaard, Rasmus Laurvig, Huang, Junwen, Busam, Benjamin, Birdal, Tolga
Object pose distribution estimation is crucial in robotics for better path planning and handling of symmetric objects. Recent distribution estimation approaches employ contrastive learning-based approaches by maximizing the likelihood of a single pos
Externí odkaz:
http://arxiv.org/abs/2409.06683
Recent learning methods for object pose estimation require resource-intensive training for each individual object instance or category, hampering their scalability in real applications when confronted with previously unseen objects. In this paper, we
Externí odkaz:
http://arxiv.org/abs/2403.01517
Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without using any
Externí odkaz:
http://arxiv.org/abs/2302.03640
Autor:
Yu, Zhibo, Wang, Jun, Zhang, Cheng, Zhan, Qiuna, Shi, Leqian, Song, Bing, Han, Danlu, Jiang, Jieming, Huang, Junwen, Ou, Xiaolin, Zhang, Zhonghui, Lai, Jianbin, Li, Qingshun Quinn, Yang, Chengwei
Publikováno v:
In Molecular Plant 2 September 2024 17(9):1392-1406
Publikováno v:
In Engineering Structures 1 December 2024 320
Autor:
Chen, Ying, Huang, Junwen, Li, Yuemao, Chen, Yaoxin, Gong, Zhaoqian, Xu, Maosheng, Ma, Yanyan, Hu, Dapeng, Peng, Xianru, Xu, Guilin, Cai, Shaoxi, Liu, Laiyu, Zhao, Wenqu, Zhao, Haijin
Publikováno v:
In Biomedicine & Pharmacotherapy August 2024 177
We introduce the concept of geometric stability to the problem of 6D object pose estimation and propose to learn pose inference based on geometrically stable patches extracted from observed 3D point clouds. According to the theory of geometric stabil
Externí odkaz:
http://arxiv.org/abs/2102.09334
Autor:
Wang, Zhuohang, Zheng, Zijian, Huang, Junwen, Cai, Xu, Liu, Xinjie, Xue, Cheng, Yao, Longping, Lu, Guohui
Publikováno v:
In Heliyon 29 February 2024 10(4)
Publikováno v:
ACM Transactions on Graphics (Proceeding of SIGGRAPH Asia), 2020
We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectiona
Externí odkaz:
http://arxiv.org/abs/2008.00485
Publikováno v:
In Composite Structures 1 September 2023 319