TWJianNuo

We have an algoritgmn to clean out the occlusion points in the scan due to the position difference between rgb camera and lidar scanner, but require a stable relative position...

Oh, I should read previous questions more carefully. That really helps a lot. But do we have the calibration matrix to convert Lidar Ego coordinate to camera coordinates? If not...

Sorry for I find out the problem so late. Can we also have the raw solid state lidar groudtruth as well? In the provided additonal lidar scan file, they are...

Hi. For some reason I can not type Chinese in this Computer. But yes, this is the official Release of the Paper. The code quality will be improved in the...

According to their [paper](http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhu_Improving_Semantic_Segmentation_via_Video_Propagation_and_Label_Relaxation_CVPR_2019_paper.pdf), it is pretrained on Cityscape and finetuned with kitti 200 semantics segmentation label.

Oh, It seems he removes pretrained model on kitti, strange. I used the model provided by the author.(but I do not know whether I still keep that.) In my memory,...

We consider handling object movement will be the core for monocular images learning. However, the proposed methods will not be helpful regarding that. But if only consider Performance, it is...

Hi, we already relaeased it. Please read description in setup section again, thanks.

Hi! Yes, the $x$ will be replaced by $x^{}$. To be more specific, the computation of $x^{}$ finally follow equation (9) to compromise among multiple depth-semantic edge pairs.

For one semantic edge pixel, it will be paired with a nearest depth edge pixel. If no depth edge pixel present near it, then we skip. After matching, we suppress...