Zz2022

> export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$CONDA_PREFIX/lib/ I sol > I was also getting this error. I don't know the details of what was happening, but the issue for me seemed to stem from...

Same problem, are there any solutions?

I think I have solved this problem, this is mainly due to the openCV3.3.1 intergrated in the ROS and you should change the path in the cv_bridge for your Opencv....

Hi, I am also trying to train it on my own datasets, my validation images can predict good results however the validation video outputs are blurred/colorful also. I tried to...

Hi, I have the same issue here, and it seems like the code stuck here: pers_points, pers_index_ray, pers_index_tri = mesh.ray.intersects_location( pers_origins, pers_vectors, multiple_hits=True) in render_utils.py line 173 and then the...

Hi, I think the problem is because the rtree required by trimesh, and it can be solved by installing trimesh using: pip install trimesh[easy] make sure uninstall the original trimesh...

Also, in the paper, you mentioned that the method is tested with 1024*1024 resolution and 512*512 with different inference speeds, Did you retrain the model under different resolutions with modified...

Hi, sorry for the late reply, I was traveling and did not have access to my PC.    Here are the normal predicted and normal from depth. I...

Also, when I trained the first stage with background image augmentation, the model can not predict good down-scaled normal, it ended with a black image predicted as I have shown...

Hi, However, in this issue, you mentioned that the input for the model prediction model should be trained with a black background. What is the difference between the black background...