[PyTorch] Official implementation of CVPR2022 paper "TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers". https://arxiv.org/abs/2203.11496
Dear authors；
I have compared tools/data_converter/nuscenes_converter.py#L246 between your code and mmdet3d offcial code,I find that you have changed yaw value by (-rots - np.pi/2),what does that means?I am confused because I need figure out yaw's coordinate system in gt_bbox；could you explain this part,thanks！
Dear authors； I have compared tools/data_converter/nuscenes_converter.py#L246 between your code and mmdet3d offcial code,I find that you have changed yaw value by (-rots - np.pi/2),what does that means?I am confused because I need figure out yaw's coordinate system in gt_bbox；could you explain this part,thanks！