Bo Yang

@lelouedec in your case where the number of gt bbox(T) is less than pred bbox(H), you need to use "the matched top T bbox" from the pred bbox to caculate...

Hi @lelouedec, according to ur code, u already made "significant" changes. Your approach is to sort all predictions based on the predicted bbox scores, while our network is to sort...

Hi @lelouedec , essentially, the released code deals with the cases where the real number of gt bbox is not equal to that of pred bbox. To be specific, in...

@lelouedec https://github.com/Yang7879/3D-BoNet/blob/07c99e58f7f1a646c211c150cb7b3c363fdd69d9/helper_net.py#L252

hi @lelouedec Thanks for sharing. Will check it out once I finish my task at hand.

Hi @chrischoy , thanks for your interest in our paper. (1) The results can indeed be different from the paper if the model is trained again. It can be better...

Hi @vvaibhav08 , if the backbone network is the pnet++ as we used in the paper, I agree that to partition the outdoor point clouds into slightly larger blocks is...

hi @LiuShihHung , the question you raised also confused me when I was doing experients. Basically, the widely used "all points" does not mean all raw points of the original...

@LiuShihHung (1) The SCN is trained on the whole scenes as same as its released code, so each 3D point will have a predicted semantic label afterwards. You could save...

Hi @neshatbln, if you want to get the final precision and recall scores, please run the evaluation script after training. https://github.com/Yang7879/3D-BoNet/blob/master/main_eval.py