Zobrazeno 1 - 10
of 376
pro vyhledávání: '"Yang Honghui"'
Autor:
Yang, Honghui, Huang, Di, Yin, Wei, Shen, Chunhua, Liu, Haifeng, He, Xiaofei, Lin, Binbin, Ouyang, Wanli, He, Tong
Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two ke
Externí odkaz:
http://arxiv.org/abs/2410.10815
In this paper, we introduce SPA, a novel representation learning framework that emphasizes the importance of 3D spatial awareness in embodied AI. Our approach leverages differentiable neural rendering on multi-view images to endow a vanilla Vision Tr
Externí odkaz:
http://arxiv.org/abs/2410.08208
Autor:
Zhu, Haoyi, Yang, Honghui, Wu, Xiaoyang, Huang, Di, Zhang, Sha, He, Xianglong, Zhao, Hengshuang, Shen, Chunhua, Qiao, Yu, He, Tong, Ouyang, Wanli
In contrast to numerous NLP and 2D vision foundational models, learning a 3D foundational model poses considerably greater challenges. This is primarily due to the inherent data variability and diversity of downstream tasks. In this paper, we introdu
Externí odkaz:
http://arxiv.org/abs/2310.08586
Autor:
Yang, Honghui, Zhang, Sha, Huang, Di, Wu, Xiaoyang, Zhu, Haoyi, He, Tong, Tang, Shixiang, Zhao, Hengshuang, Qiu, Qibo, Lin, Binbin, He, Xiaofei, Ouyang, Wanli
In the context of autonomous driving, the significance of effective feature learning is widely acknowledged. While conventional 3D self-supervised pre-training methods have shown widespread success, most methods follow the ideas originally designed f
Externí odkaz:
http://arxiv.org/abs/2310.08370
Autor:
Qiu, Qibo, Yang, Honghui, Wang, Wenxiao, Zhang, Shun, Gao, Haiming, Ying, Haochao, Hua, Wei, He, Xiaofei
Masked point modeling has become a promising scheme of self-supervised pre-training for point clouds. Existing methods reconstruct either the original points or related features as the objective of pre-training. However, considering the diversity of
Externí odkaz:
http://arxiv.org/abs/2309.13235
Autor:
Yang, Honghui, Wang, Wenxiao, Chen, Minghao, Lin, Binbin, He, Tong, Chen, Hua, He, Xiaofei, Ouyang, Wanli
Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper, we present
Externí odkaz:
http://arxiv.org/abs/2305.06621
We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering. Motivated by the fact that informative point cloud features should be able to encode rich geometry and appearance cues and rend
Externí odkaz:
http://arxiv.org/abs/2301.00157
Autor:
Yang, Honghui, He, Tong, Liu, Jiaheng, Chen, Hua, Wu, Boxi, Lin, Binbin, He, Xiaofei, Ouyang, Wanli
Despite the tremendous progress of Masked Autoencoders (MAE) in developing vision tasks such as image and video, exploring MAE in large-scale 3D point clouds remains challenging due to the inherent irregularity. In contrast to previous 3D MAE framewo
Externí odkaz:
http://arxiv.org/abs/2212.03010
Autor:
Liu, Jiaheng, He, Tong, Yang, Honghui, Su, Rui, Tian, Jiayi, Wu, Junran, Guo, Hongcheng, Xu, Ke, Ouyang, Wanli
Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness. Besides, inevitable variations of different datasets make these methods become particularly sensitive t
Externí odkaz:
http://arxiv.org/abs/2211.09375
Two-stage detectors have gained much popularity in 3D object detection. Most two-stage 3D detectors utilize grid points, voxel grids, or sampled keypoints for RoI feature extraction in the second stage. Such methods, however, are inefficient in handl
Externí odkaz:
http://arxiv.org/abs/2208.03624