Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Hou, Yuenan"'
Training deep learning models for semantic occupancy prediction is challenging due to factors such as a large number of occupancy cells, severe occlusion, limited visual cues, complicated driving scenarios, etc. Recent methods often adopt transformer
Externí odkaz:
http://arxiv.org/abs/2408.09859
Autor:
Wu, Xiaopei, Peng, Liang, Xie, Liang, Hou, Yuenan, Lin, Binbin, Huang, Xiaoshui, Liu, Haifeng, Cai, Deng, Ouyang, Wanli
Semi-supervised learning aims to leverage numerous unlabeled data to improve the model performance. Current semi-supervised 3D object detection methods typically use a teacher to generate pseudo labels for a student, and the quality of the pseudo lab
Externí odkaz:
http://arxiv.org/abs/2407.09787
Autor:
Wu, Xiaopei, Hou, Yuenan, Huang, Xiaoshui, Lin, Binbin, He, Tong, Zhu, Xinge, Ma, Yuexin, Wu, Boxi, Liu, Haifeng, Cai, Deng, Ouyang, Wanli
Training deep models for LiDAR semantic segmentation is challenging due to the inherent sparsity of point clouds. Utilizing temporal data is a natural remedy against the sparsity problem as it makes the input signal denser. However, previous multi-fr
Externí odkaz:
http://arxiv.org/abs/2407.09751
Synthetic aperture radar (SAR) is essential in actively acquiring information for Earth observation. SAR Automatic Target Recognition (ATR) focuses on detecting and classifying various target categories under different image conditions. The current d
Externí odkaz:
http://arxiv.org/abs/2405.09365
Autor:
Huang, Chenxi, Hou, Yuenan, Ye, Weicai, Huang, Di, Huang, Xiaoshui, Lin, Binbin, Cai, Deng, Ouyang, Wanli
NeRF-Det has achieved impressive performance in indoor multi-view 3D detection by innovatively utilizing NeRF to enhance representation learning. Despite its notable performance, we uncover three decisive shortcomings in its current design, including
Externí odkaz:
http://arxiv.org/abs/2402.14464
Autor:
Liu, Jian, Huang, Xiaoshui, Huang, Tianyu, Chen, Lu, Hou, Yuenan, Tang, Shixiang, Liu, Ziwei, Ouyang, Wanli, Zuo, Wangmeng, Jiang, Junjun, Liu, Xianming
Recent years have witnessed remarkable advances in artificial intelligence generated content(AIGC), with diverse input modalities, e.g., text, image, video, audio and 3D. The 3D is the most close visual modality to real-world 3D environment and carri
Externí odkaz:
http://arxiv.org/abs/2402.01166
Autor:
Liu, Dingning, Huang, Xiaoshui, Hou, Yuenan, Wang, Zhihui, Yin, Zhenfei, Gong, Yongshun, Gao, Peng, Ouyang, Wanli
In this paper, we introduce Uni3D-LLM, a unified framework that leverages a Large Language Model (LLM) to integrate tasks of 3D perception, generation, and editing within point cloud scenes. This framework empowers users to effortlessly generate and
Externí odkaz:
http://arxiv.org/abs/2402.03327
Autor:
Li, Weijie, Wei, Yang, Liu, Tianpeng, Hou, Yuenan, Li, Yuxuan, Liu, Zhen, Liu, Yongxiang, Liu, Li
The growing Synthetic Aperture Radar (SAR) data has the potential to build a foundation model through Self-Supervised Learning (SSL) methods, which can achieve various SAR Automatic Target Recognition (ATR) tasks with pre-training in large-scale unla
Externí odkaz:
http://arxiv.org/abs/2311.15153
Autor:
Liu, Youquan, Chen, Runnan, Li, Xin, Kong, Lingdong, Yang, Yuchen, Xia, Zhaoyang, Bai, Yeqi, Zhu, Xinge, Ma, Yuexin, Li, Yikang, Qiao, Yu, Hou, Yuenan
Point-, voxel-, and range-views are three representative forms of point clouds. All of them have accurate 3D measurements but lack color and texture information. RGB images are a natural complement to these point cloud views and fully utilizing the c
Externí odkaz:
http://arxiv.org/abs/2309.05573
Autor:
Xu, Yiteng, Cong, Peishan, Yao, Yichen, Chen, Runnan, Hou, Yuenan, Zhu, Xinge, He, Xuming, Yu, Jingyi, Ma, Yuexin
Human-centric scene understanding is significant for real-world applications, but it is extremely challenging due to the existence of diverse human poses and actions, complex human-environment interactions, severe occlusions in crowds, etc. In this p
Externí odkaz:
http://arxiv.org/abs/2307.14392