Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
This addresses the problem of accurate and cost-effective 3D object detection for autonomous driving, offering a competitive solution without reliance on LiDAR annotations.
The paper tackles 3D object detection from stereo images by proposing Disp R-CNN, which uses instance disparity estimation with category-specific shape priors and pseudo-ground-truth generation, achieving a 20% improvement in average precision on KITTI without LiDAR training data.
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.