1 code implementation • 14 Feb 2024 • Xiuzhong Hu, Guangming Xiong, Zheng Zang, Peng Jia, Yuxuan Han, Junyi Ma
With extensive experiments, PC-NeRF is proven to achieve high-precision novel LiDAR view synthesis and 3D reconstruction in large-scale scenes.
1 code implementation • 6 Nov 2023 • Zijie Zhou, Jingyi Xu, Guangming Xiong, Junyi Ma
However, most existing multimodal place recognition methods only use limited field-of-view camera images, which leads to an imbalance between features from different modalities and limits the effectiveness of sensor fusion.
1 code implementation • 2 Oct 2023 • Xiuzhong Hu, Guangming Xiong, Zheng Zang, Peng Jia, Yuxuan Han, Junyi Ma
Reconstructing large-scale 3D scenes is essential for autonomous vehicles, especially when partial sensor data is lost.
1 code implementation • 16 Apr 2023 • Zhen Luo, Junyi Ma, Zijie Zhou, Guangming Xiong
In this letter, we propose a novel efficient Transformer-based network to predict the future LiDAR point clouds exploiting the past point cloud sequences.
1 code implementation • 3 Feb 2023 • Junyi Ma, Guangming Xiong, Jingyi Xu, Xieyuanli Chen
LiDAR-based place recognition (LPR) is one of the most crucial components of autonomous vehicles to identify previously visited places in GPS-denied environments.
1 code implementation • 16 Sep 2022 • Junyi Ma, Xieyuanli Chen, Jingyi Xu, Guangming Xiong
It uses multi-scale transformers to generate a global descriptor for each sequence of LiDAR range images in an end-to-end fashion.