Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection

by   Yinmin Zhang, et al.

As a crucial task of autonomous driving, 3D object detection has made great progress in recent years. However, monocular 3D object detection remains a challenging problem due to the unsatisfactory performance in depth estimation. Most existing monocular methods typically directly regress the scene depth while ignoring important relationships between the depth and various geometric elements (e.g. bounding box sizes, 3D object dimensions, and object poses). In this paper, we propose to learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection. Specifically, a principled geometry formula with projective modeling of 2D and 3D depth predictions in the monocular 3D object detection network is devised. We further implement and embed the proposed formula to enable geometry-aware deep representation learning, allowing effective 2D and 3D interactions for boosting the depth estimation. Moreover, we provide a strong baseline through addressing substantial misalignment between 2D annotation and projected boxes to ensure robust learning with the proposed geometric formula. Experiments on the KITTI dataset show that our method remarkably improves the detection performance of the state-of-the-art monocular-based method without extra data by 2.80 moderate test setting. The model and code will be released at https://github.com/YinminZhang/MonoGeo.


page 8

page 13

page 14

page 15

page 16


MonoGRNet: A General Framework for Monocular 3D Object Detection

Detecting and localizing objects in the real 3D space, which plays a cru...

Objects are Different: Flexible Monocular 3D Object Detection

The precise localization of 3D objects from a single image without depth...

Densely Constrained Depth Estimator for Monocular 3D Object Detection

Estimating accurate 3D locations of objects from monocular images is a c...

Geometry Uncertainty Projection Network for Monocular 3D Object Detection

Geometry Projection is a powerful depth estimation method in monocular 3...

Monocular 3D Object Detection with Depth from Motion

Perceiving 3D objects from monocular inputs is crucial for robotic syste...

Long Range Object-Level Monocular Depth Estimation for UAVs

Computer vision-based object detection is a key modality for advanced De...

Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraints

We propose Shift R-CNN, a hybrid model for monocular 3D object detection...

Please sign up or login with your details

Forgot password? Click here to reset