3D_Corruptions_AD
3D_Corruptions_AD copied to clipboard
Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving, CVPR 2023
这个工作针对的是离线的图片数据,我想问一下如果是自动驾驶视频实时情况,这些噪声可以加上去么,有点困难吧。
Why is the weather level corruption higher than the AP with clean data in KITTI-C pedestrian detection, resulting in a negative RCE, which is clearly contrary to common sense
I had a lot of problems configuring the environment for this project, does anyone know the details of the recommended environment configuration?
Thank you for your research. I'm trying to run the provided source code, but I don't know how to run it. Please let me know how do i run this...
How is the results['cam_sweeps'] in nuscenes Dataset generated? 
There are some codes in bbox_util.py: `MAP = { 'density_dec_bbox':density, 'cutout_bbox':cutout, 'gaussian_noise_bbox':gaussian, 'uniform_noise_bbox':uniform, 'impulse_noise_bbox':impulse, 'scale_bbox':scale, 'shear_bbox':shear, 'rotation_bbox':rotation, 'moving_noise_bbox':moving_object, }` and ` if 'bbox' in cor: pcd_2 = MAP[cor](pcd_2, slevel, gt_boxes)...
MMdetection3D已经升级了,现在还是2.0.0以前的版本,导致已经跑不通了。请问现在的代码还会更新么