Some confusion and a request

[mrsempress]

First of all, thank you for your excellent work. But I have some confusion and a request.
1.kitti_dataset 27 lines of the code, you load label in 'ddmp', not the provided "label_2". What preprocessing did you do to the label? I did not find an explanation in your paper.
2. As you said in the paper, the performance of the 2D detector has no positive correlation with the final 3D detection accuracy. So how do I choose a 2D detector, because I cannot choose the best 2D detector?
3. Have you done other coordinate-based detector experiments, because the paper only reports PatchNet+PCT.
4. Can you provide the feature files of the two-dimensional detection in training and testing so that I can run the code?

[mrsempress]

For 4, are you using the model released by RTM3D? If so, which model are you using (there are two models for the same backbone); if not, can you provide the cpkt or details?

[Willy0919]

First of all, thank you for your excellent work. But I have some confusion and a request. 1.kitti_dataset 27 lines of the code, you load label in 'ddmp', not the provided "label_2". What preprocessing did you do to the label? I did not find an explanation in your paper. 2. As you said in the paper, the performance of the 2D detector has no positive correlation with the final 3D detection accuracy. So how do I choose a 2D detector, because I cannot choose the best 2D detector? 3. Have you done other coordinate-based detector experiments, because the paper only reports PatchNet+PCT. 4. Can you provide the feature files of the two-dimensional detection in training and testing so that I can run the code?

1. We use the 2D bounding boxes from existing detector for our coordinate proposal generation, hence you can use your own generated 2D bounding box labels here. Please refer to line 83 tools/data_prepare/patch_data_prepare_val.py
2. We find that the accuracy of the 3D detector is not positively related to the accuracy of the 2D detector, and our results are not the best performance. Hence, how to choose the best 2D detector should be explored in the future works.
3. We have also conducted the experiments of Pseudo LiDAR + PCT, please refer to the section 'Generally applicable to other coordinate-based algorithm' in our paper.
4. Please generate the feature files following the Readme.md as it is too large to share. You can use the second model from RTM3D (DLA_34) trained only on train split as the fourth one has introduced the additional right images.