zhixy

How about putting the global network on CPU, and each local network on one GPU? It should be easy to implement

Hi, I suffered a Segmentation fault (core dumped) error, even though I finally got the segmentation result. `python inference.py ../elephant.jpg ./deeplab_resnet.ckpt W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use...

Hi, Actually, 'Calib_Result.mat' is generated by the calibration toolbox [here](http://www.vision.caltech.edu/bouguetj/calib_doc/), rather than the one embedded inside MATLAB, so the second problem should be fixed by using the correct calibration toolbox....

Hello， I think VLP-16 is good enough, if you wanna improve the precision of calibration, please use as many of point clouds and images as possible. Also, there is an...

Hi, thx for your attention, we are working on some thorough experiments to evaluation our algorithms, after finishing these experiments, a paper will come soon.

Hi, glad to hear that multical help you research! Yeah, the paper is a little bit late, mainly because I have job to do, so very less spare time to...

Thank you for your appreciation, the paper will come very soon