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.
@article{arxiv.2004.03572,
title = {Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation},
author = {Jiaming Sun and Linghao Chen and Yiming Xie and Siyu Zhang and Qinhong Jiang and Xiaowei Zhou and Hujun Bao},
journal= {arXiv preprint arXiv:2004.03572},
year = {2020}
}
Comments
Accepted to CVPR 2020. Code is available at https://github.com/zju3dv/disprcnn