Monocular 3D Object Detection via Geometric Reasoning on Keypoints

TL;DR

This paper introduces a novel monocular 3D object detection method that combines 2D keypoint detection with geometric reasoning, achieving state-of-the-art results on the KITTI dataset.

Contribution

It presents an end-to-end multi-branch network that jointly estimates 2D and 3D object attributes using geometric reasoning, improving monocular 3D detection accuracy.

Findings

Achieves state-of-the-art results on KITTI benchmark.

Effectively combines 2D keypoints with geometric reasoning.

End-to-end training improves detection consistency.

Abstract

Monocular 3D object detection is well-known to be a challenging vision task due to the loss of depth information; attempts to recover depth using separate image-only approaches lead to unstable and noisy depth estimates, harming 3D detections. In this paper, we propose a novel keypoint-based approach for 3D object detection and localization from a single RGB image. We build our multi-branch model around 2D keypoint detection in images and complement it with a conceptually simple geometric reasoning method. Our network performs in an end-to-end manner, simultaneously and interdependently estimating 2D characteristics, such as 2D bounding boxes, keypoints, and orientation, along with full 3D pose in the scene. We fuse the outputs of distinct branches, applying a reprojection consistency loss during training. The experimental evaluation on the challenging KITTI dataset benchmark demonstrates that our network achieves state-of-the-art results among other monocular 3D detectors.