no code implementations • 18 Mar 2024 • Ziying Song, Lei Yang, Shaoqing Xu, Lin Liu, Dongyang Xu, Caiyan Jia, Feiyang Jia, Li Wang
Additionally, we propose a Global Align module to rectify the misalignment between LiDAR and camera BEV features.
no code implementations • 8 Jan 2024 • Ziying Song, Guoxing Zhang, Lin Liu, Lei Yang, Shaoqing Xu, Caiyan Jia, Feiyang Jia, Li Wang
To align SAM or SAM-AD with multi-modal methods, we then introduce AD-FPN for upsampling the image features extracted by SAM.
no code implementations • 5 Jan 2024 • Ziying Song, Guoxin Zhang, Jun Xie, Lin Liu, Caiyan Jia, Shaoqing Xu, Zhepeng Wang
In particular, we propose a voxel-based image pipeline that involves projecting point clouds onto images to obtain both pixel- and patch-level features.
no code implementations • 15 Jun 2023 • Mingjie Pan, Li Liu, Jiaming Liu, Peixiang Huang, Longlong Wang, Shanghang Zhang, Shaoqing Xu, Zhiyi Lai, Kuiyuan Yang
In this technical report, we present our solution, named UniOCC, for the Vision-Centric 3D occupancy prediction track in the nuScenes Open Dataset Challenge at CVPR 2023.
Ranked #3 on Prediction Of Occupancy Grid Maps on Occ3D-nuScenes
no code implementations • 10 Dec 2022 • Shaoqing Xu, Fang Li, Ziying Song, Jin Fang, Sifen Wang, Zhi-Xin Yang
Most multi-modal 3D object detection frameworks integrate semantic knowledge from 2D images into 3D LiDAR point clouds to enhance detection accuracy.
1 code implementation • 23 Jun 2021 • Shaoqing Xu, Dingfu Zhou, Jin Fang, Junbo Yin, Zhou Bin, Liangjun Zhang
Then the segmentation results from different sensors are adaptively fused based on the proposed attention-based semantic fusion module.