Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

by   Yang You, et al.

3D object detection has attracted much attention thanks to the advances in sensors and deep learning methods for point clouds. Current state-of-the-art methods like VoteNet regress direct offset towards object centers and box orientations with an additional Multi-Layer-Perceptron network. Both their offset and orientation predictions are not accurate due to the fundamental difficulty in rotation classification. In the work, we disentangle the direct offset into Local Canonical Coordinates (LCC), box scales and box orientations. Only LCC and box scales are regressed while box orientations are generated by a canonical voting scheme. Finally, a LCC-aware back-projection checking algorithm iteratively cuts out bounding boxes from the generated vote maps, with the elimination of false positives. Our model achieves state-of-the-art performance on challenging large-scale datasets of real point cloud scans: ScanNet, SceneNN with 11.4 and 5.3 mAP improvement respectively. Code is available on



There are no comments yet.


page 1

page 3

page 6

page 7

page 8


Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectors

Oriented object detection in aerial images is a challenging task as the ...

Center-based 3D Object Detection and Tracking

Three-dimensional objects are commonly represented as 3D boxes in a poin...

Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds

3D object detection in point clouds is a challenging vision task that be...

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

Recently, promising applications in robotics and augmented reality have ...

Towards Rotation Invariance in Object Detection

Rotation augmentations generally improve a model's invariance/equivarian...

IterDet: Iterative Scheme for ObjectDetection in Crowded Environments

Deep learning-based detectors usually produce a redundant set of object ...

LMNet: Real-time Multiclass Object Detection on CPU using 3D LiDARs

This paper describes an optimized single-stage deep convolutional neural...

Code Repositories


Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.