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.

中文翻译：

---

Disp R-CNN：通过形状先验引导实例视差估计进行立体 3D 对象检测

在本文中，我们提出了一种名为 Disp R-CNN 的新系统，用于从立体图像中检测 3D 对象。最近的许多工作通过首先使用视差估计恢复点云然后应用 3D 检测器来解决这个问题。为整个图像计算视差图，这代价高昂并且无法利用特定类别的先验。相比之下，我们设计了一个实例视差估计网络 (iDispNet)，它仅预测感兴趣对象上的像素的视差，并先学习特定类别的形状以进行更准确的视差估计。为了解决训练中视差注释稀缺的挑战，我们建议使用统计形状模型生成密集视差伪地面实况，而无需 LiDAR 点云，这使我们的系统更广泛适用。