Zobrazeno 1 - 10
of 2 284
pro vyhledávání: '"Pu, Jian"'
High-definition (HD) maps are essential for autonomous driving systems. Traditionally, an expensive and labor-intensive pipeline is implemented to construct HD maps, which is limited in scalability. In recent years, crowdsourcing and online mapping h
Externí odkaz:
http://arxiv.org/abs/2409.10063
In this paper, we generalize the Weyl double copy to five-dimensional spacetime. We show that a special class of five-dimensional type N vacuum solutions admits a special class of degenerate Maxwell field that squares to give the Weyl tensor. The fiv
Externí odkaz:
http://arxiv.org/abs/2409.06786
Publikováno v:
ECCV 2024
In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not require com
Externí odkaz:
http://arxiv.org/abs/2407.13254
Deep supervised models possess significant capability to assimilate extensive training data, thereby presenting an opportunity to enhance model performance through training on multiple datasets. However, conflicts arising from different label spaces
Externí odkaz:
http://arxiv.org/abs/2407.10534
In recent years, the integration of prediction and planning through neural networks has received substantial attention. Despite extensive studies on it, there is a noticeable gap in understanding the operation of such models within a closed-loop plan
Externí odkaz:
http://arxiv.org/abs/2407.05376
Autor:
He, Zhuolin, Li, Xinrun, Gao, Heng, Tang, Jiachen, Qiu, Shoumeng, Wang, Wenfu, Lu, Lvjian, Qiu, Xuchong, Xue, Xiangyang, Pu, Jian
Traditional camera 3D object detectors are typically trained to recognize a predefined set of known object classes. In real-world scenarios, these detectors may encounter unknown objects outside the training categories and fail to identify them corre
Externí odkaz:
http://arxiv.org/abs/2406.17297
Out-of-distribution (OOD) detection methods have been developed to identify objects that a model has not seen during training. The Outlier Exposure (OE) methods use auxiliary datasets to train OOD detectors directly. However, the collection and learn
Externí odkaz:
http://arxiv.org/abs/2406.16525
We introduce EC-SLAM, a real-time dense RGB-D simultaneous localization and mapping (SLAM) system utilizing Neural Radiance Fields (NeRF). Although recent NeRF-based SLAM systems have demonstrated encouraging outcomes, they have yet to completely lev
Externí odkaz:
http://arxiv.org/abs/2404.13346
Autor:
Hou, Jiawei, Li, Xiaoyan, Guan, Wenhao, Zhang, Gang, Feng, Di, Du, Yuheng, Xue, Xiangyang, Pu, Jian
In autonomous driving, 3D occupancy prediction outputs voxel-wise status and semantic labels for more comprehensive understandings of 3D scenes compared with traditional perception tasks, such as 3D object detection and bird's-eye view (BEV) semantic
Externí odkaz:
http://arxiv.org/abs/2403.02710
Autor:
Jiang, Feng, Tu, Chaoping, Zhang, Gang, Li, Jun, Huang, Hanqing, Lin, Junyu, Feng, Di, Pu, Jian
LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios. However, existing multi-modal methods face two key challenges:
Externí odkaz:
http://arxiv.org/abs/2310.08826