Good and fast 3D object detection by using simulated depth data
Good and fast 3D object detection by using simulated depth data
Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
arXiv paper abstract https://arxiv.org/abs/2107.13269v1
arXiv PDF paper https://arxiv.org/pdf/2107.13269v1.pdf
Current geometry-based monocular 3D object detection models can efficiently detect objects by leveraging perspective geometry, but their performance is limited due to the absence of accurate depth information.
… propose a rendering module to augment the training data by synthesizing images with virtual-depths.
The rendering module takes as input the RGB image and its corresponding sparse depth image, outputs a variety of photo-realistic synthetic images, from which the detection model can learn more discriminative features to adapt to the depth changes of the objects.
… Both modules are working in the training time and no extra computation will be introduced to the detection model.
… leading accuracy on the KITTI 3D detection benchmark.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
