Zobrazeno 1 - 10
of 27
pro vyhledávání: '"Lou, Yujing"'
Autor:
Lin, Jingyu, Gu, Jiaqi, Fan, Lubin, Wu, Bojian, Lou, Yujing, Chen, Renjie, Liu, Ligang, Ye, Jieping
Generating high-quality novel view renderings of 3D Gaussian Splatting (3DGS) in scenes featuring transient objects is challenging. We propose a novel hybrid representation, termed as HybridGS, using 2D Gaussians for transient objects per image and m
Externí odkaz:
http://arxiv.org/abs/2412.03844
Autor:
Lou, Yujing, Ye, Zelin, You, Yang, Jiang, Nianjuan, Lu, Jiangbo, Wang, Weiming, Ma, Lizhuang, Lu, Cewu
Various recent methods attempt to implement rotation-invariant 3D deep learning by replacing the input coordinates of points with relative distances and angles. Due to the incompleteness of these low-level features, they have to undertake the expense
Externí odkaz:
http://arxiv.org/abs/2303.03101
Autor:
You, Yang, Li, Chengkun, Lou, Yujing, Cheng, Zhoujun, Li, Liangwei, Ma, Lizhuang, Wang, Weiming, Lu, Cewu
Pixel-level 2D object semantic understanding is an important topic in computer vision and could help machine deeply understand objects (e.g. functionality and affordance) in our daily life. However, most previous methods directly train on corresponde
Externí odkaz:
http://arxiv.org/abs/2111.10817
Soft-argmax operation is commonly adopted in detection-based methods to localize the target position in a differentiable manner. However, training the neural network with soft-argmax makes the shape of the probability map unconstrained. Consequently,
Externí odkaz:
http://arxiv.org/abs/2110.08825
Autor:
You, Yang, Lou, Yujing, Shi, Ruoxi, Liu, Qi, Tai, Yu-Wing, Ma, Lizhuang, Wang, Weiming, Lu, Cewu
Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Point-wise Rotation Invariant N
Externí odkaz:
http://arxiv.org/abs/2102.12093
Autor:
You, Yang, Ye, Zelin, Lou, Yujing, Li, Chengkun, Li, Yong-Lu, Ma, Lizhuang, Wang, Weiming, Lu, Cewu
3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations with an add
Externí odkaz:
http://arxiv.org/abs/2011.12001
Visual semantic correspondence is an important topic in computer vision and could help machine understand objects in our daily life. However, most previous methods directly train on correspondences in 2D images, which is end-to-end but loses plenty o
Externí odkaz:
http://arxiv.org/abs/2004.09061
Autor:
You, Yang, Lou, Yujing, Li, Chengkun, Cheng, Zhoujun, Li, Liangwei, Ma, Lizhuang, Wang, Weiming, Lu, Cewu
Detecting 3D objects keypoints is of great interest to the areas of both graphics and computer vision. There have been several 2D and 3D keypoint datasets aiming to address this problem in a data-driven way. These datasets, however, either lack scala
Externí odkaz:
http://arxiv.org/abs/2002.12687
Autor:
Lou, Yujing, You, Yang, Li, Chengkun, Cheng, Zhoujun, Li, Liangwei, Ma, Lizhuang, Wang, Weiming, Lu, Cewu
Semantic understanding of 3D objects is crucial in many applications such as object manipulation. However, it is hard to give a universal definition of point-level semantics that everyone would agree on. We observe that people have a consensus on sem
Externí odkaz:
http://arxiv.org/abs/1912.12577
Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Pointwise Rotation-Invariant Ne
Externí odkaz:
http://arxiv.org/abs/1811.09361