Zobrazeno 1 - 10
of 103
pro vyhledávání: '"Zhu, Xinge"'
In this paper, we propose an algorithm for registering sequential bounding boxes with point cloud streams. Unlike popular point cloud registration techniques, the alignment of the point cloud and the bounding box can rely on the properties of the bou
Externí odkaz:
http://arxiv.org/abs/2409.09312
Large Vision-Language Models (LVLMs) have recently garnered significant attention, with many efforts aimed at harnessing their general knowledge to enhance the interpretability and robustness of autonomous driving models. However, LVLMs typically rel
Externí odkaz:
http://arxiv.org/abs/2409.02914
We introduce Multi-Cylindrical Panoramic Depth Estimation (MCPDepth), a two-stage framework for omnidirectional depth estimation via stereo matching between multiple cylindrical panoramas. MCPDepth uses cylindrical panoramas for initial stereo matchi
Externí odkaz:
http://arxiv.org/abs/2408.01653
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
Human-centric Point Cloud Video Understanding (PVU) is an emerging field focused on extracting and interpreting human-related features from sequences of human point clouds, further advancing downstream human-centric tasks and applications. Previous w
Externí odkaz:
http://arxiv.org/abs/2403.20031
Autor:
Cong, Peishan, Wang, Ziyi, Dou, Zhiyang, Ren, Yiming, Yin, Wei, Cheng, Kai, Sun, Yujing, Long, Xiaoxiao, Zhu, Xinge, Ma, Yuexin
Language-guided scene-aware human motion generation has great significance for entertainment and robotics. In response to the limitations of existing datasets, we introduce LaserHuman, a pioneering dataset engineered to revolutionize Scene-Text-to-Mo
Externí odkaz:
http://arxiv.org/abs/2403.13307
Human-centric 3D scene understanding has recently drawn increasing attention, driven by its critical impact on robotics. However, human-centric real-life scenarios are extremely diverse and complicated, and humans have intricate motions and interacti
Externí odkaz:
http://arxiv.org/abs/2403.02769
Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes. Traditional approaches typically rely on dense, regular grid representations, which often leads to excessive computational deman
Externí odkaz:
http://arxiv.org/abs/2312.03774
Autor:
Peng, Xidong, Chen, Runnan, Qiao, Feng, Kong, Lingdong, Liu, Youquan, Sun, Yujing, Wang, Tai, Zhu, Xinge, Ma, Yuexin
Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes obvious acro
Externí odkaz:
http://arxiv.org/abs/2310.08820
Autor:
Chen, Runnan, Zhu, Xinge, Chen, Nenglun, Wang, Dawei, Li, Wei, Ma, Yuexin, Yang, Ruigang, Liu, Tongliang, Wang, Wenping
Current successful methods of 3D scene perception rely on the large-scale annotated point cloud, which is tedious and expensive to acquire. In this paper, we propose Model2Scene, a novel paradigm that learns free 3D scene representation from Computer
Externí odkaz:
http://arxiv.org/abs/2309.16956