Disp R-CNN: Stereo 3D object detection via shape prior guided instance disparity estimation

Sun，Jiaming1,2,4; Chen，Linghao1,4; Xie，Yiming1; Zhang，Siyu3; Jiang，Qinhong2; Zhou，Xiaowei1; Bao，Hujun1

10.1109/CVPR42600.2020.01056

2020

1063-6919

978-1-7281-7169-2

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

10545-10554

13-19 June 2020

Seattle, WA, USA

In this paper, we propose a novel system named Disp R-CNN for 3D object detection from stereo images. Many recent works solve this problem by first recovering a point cloud with disparity estimation and then apply a 3D detector. The disparity map is computed for the entire image, which is costly and fails to leverage category-specific prior. In contrast, we design an instance disparity estimation network (iDispNet) that predicts disparity only for pixels on objects of interest and learns a category-specific shape prior for more accurate disparity estimation. To address the challenge from scarcity of disparity annotation in training, we propose to use a statistical shape model to generate dense disparity pseudo-ground-truth without the need of LiDAR point clouds, which makes our system more widely applicable. Experiments on the KITTI dataset show that, even when LiDAR ground-truth is not available at training time, Disp R-CNN achieves competitive performance and outperforms previous state-of-the-art methods by 20% in terms of average precision. The code will be available at https://github.com/zju3dv/disprcnn.

Three-dimensional displays Estimation Object detection Shape Laser radar Two dimensional displays Detectors

其他

英语

EI

20204409441240

Optical radar ; Object recognition ; Computer vision ; Stereo image processing

Radar Systems and Equipment:716.2 ; Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Vision:741.2 ; Optical Devices and Systems:741.3

2-s2.0-85093931297

Scopus

1.Zhejiang University,China
2.SenseTime,
3.Southern University of Science and Technology,China
4.State Key Lab of CAD&CG,

Sun，Jiaming,Chen，Linghao,Xie，Yiming,et al. Disp R-CNN: Stereo 3D object detection via shape prior guided instance disparity estimation[C],2020:10545-10554.