MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
arXiv:2003.00504
Abstract
Monocular 3D object detection is an essential component in autonomous driving while challenging to solve, especially for those occluded samples which are only partially visible. Most detectors consider each 3D object as an independent training target, inevitably resulting in a lack of useful information for occluded samples. To this end, we propose a novel method to improve the monocular 3D object detection by considering the relationship of paired samples. This allows us to encode spatial constraints for partially-occluded objects from their adjacent neighbors. Specifically, the proposed detector computes uncertainty-aware predictions for object locations and 3D distances for the adjacent object pairs, which are subsequently jointly optimized by nonlinear least squares. Finally, the one-stage uncertainty-aware prediction structure and the post-optimization module are dedicatedly integrated for ensuring the run-time efficiency. Experiments demonstrate that our method yields the best performance on KITTI 3D detection benchmark, by outperforming state-of-the-art competitors by wide margins, especially for the hard samples.
CVPR 2020 accepted
References in corpus (6)
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Deep Continuous Fusion for Multi-Sensor 3D Object Detection
- Orthographic Feature Transform for Monocular 3D Object Detection
- Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
- Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection
- Reconstructing Vechicles from a Single Image: Shape Priors for Road Scene Understanding