ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving

Xibin Song, Peng Wang, Dingfu Zhou, Rui Zhu, Chenye Guan, Yuchao Dai, Hao Su, Hongdong Li, Ruigang Yang; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 5452-5462


Autonomous driving has attracted remarkable attention from both industry and academia. An important task is to estimate 3D properties (e.g. translation, rotation and shape) of a moving or parked vehicle on the road. This task, while critical, is still under-researched in the computer vision community - partially owing to the lack of large scale and fully-annotated 3D car database suitable for autonomous driving research. In this paper, we contribute the first large scale database suitable for 3D car instance understanding - ApolloCar3D. The dataset contains 5,277 driving images and over 60K car instances, where each car is fitted with an industry-grade 3D CAD model with absolute model size and semantically labelled keypoints. This dataset is above 20x larger than PASCAL3D+ and KITTI, the current state-of-the-art. To enable efficient labelling in 3D, we build a pipeline by considering 2D-3D keypoint correspondences for a single instance and 3D relationship among multiple instances. Equipped with such dataset, we build various baseline algorithms with the state-of-the-art deep convolutional neural networks. Specifically, we first segment each car with a pre-trained Mask R-CNN, and then regress towards its 3D pose and shape based on a deformable 3D car model with or without using semantic keypoints. We show that using keypoints significantly improves fitting performance. Finally, we develop a new 3D metric jointly considering 3D pose and 3D shape, allowing for comprehensive evaluation and ablation study.

Related Material

[pdf] [supp]
author = {Song, Xibin and Wang, Peng and Zhou, Dingfu and Zhu, Rui and Guan, Chenye and Dai, Yuchao and Su, Hao and Li, Hongdong and Yang, Ruigang},
title = {ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}