weiyithu
some confusing about this paper
hello, what make this success? I think the generated dense lidar occupancy label plays an important role in this work. If i choose another dataset, and can't generate such dense label using possion or other methods, can the proposed method works well or not? Looking forward to your reply, thanks!
Hi, Figure 7 in our arxiv paper shows a comparison of predictions supervised by dense and sparse (LiDAR points) labels. Trained with dense ground truth, the network can predict better and denser occupancy.
Although our model is better than other SOTA methods with the same ground truth, we argue that the dense groundtruth is necessary for the dense occupancy prediction task. For other dataset, you can try our ground truth generation pipeline to generate dense occupancy labels and our code supports for other datasets .
