Efficiently detect 3D objects in 2D range image with graph convolution kernels
Efficiently detect 3D objects in 2D range image with graph convolution kernels
To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels
arXiv paper abstract https://arxiv.org/abs/2106.13381
arXiv PDF paper https://arxiv.org/pdf/2106.13381.pdf
3D object detection is vital for many robotics applications.
For tasks where a 2D perspective range image exists, we propose to learn a 3D representation directly from this range image view.
... performs competitively on the Waymo Open Dataset and improves the state-of-the-art AP for pedestrian detection from 69.7% to 75.5%.
... our smallest model, which still outperforms the popular PointPillars in quality, requires 180 times fewer FLOPS and model parameters
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Bình luận