Cristian Duguet

Thank you! I tried with ``` spheric_poses += [spheric_pose(th, 0, radius*1.5)] ``` and it seems like I need to train it again because everything above the original viewpoint looks like:...

Trained the network completely with the new poses calculation, and got this:  Now I'm out of ideas. Any suggestion?

[Here are the colmap files and images.](https://drive.google.com/file/d/17Yh-Etkee4NUNkcEmTacNkR9yUqhDtgk/view?usp=sharing) [Here are the logs and the checkpoint used for the first experiment (not modifying poses). ](https://drive.google.com/file/d/1BAIKfTjI2z_v9hr5EXbKQli0iIpblviB/view?usp=sharing) [Here are the logs and checkpoint for...

I managed to make it work with [yenchenlin/nerf-pytorch](https://github.com/yenchenlin/nerf-pytorch) using the same input images/camera poses. I will try looking for the difference in your code in order to find the bug....

The reason here is that conda does not install nvcc with its cudatoolkit installation. conda's `cudatoolkit` is just a subset of Nvidia's `nvidia-cuda-toolkit`. More info on https://stackoverflow.com/questions/56470424/nvcc-missing-when-installing-cudatoolkit Be careful, however,...

I decided to use a docker container and forget about the problem

I did not have such problems until today. I wonder what changed in my system so that I have the same problem as you, 2 years afterwards.

The answer is in https://stackoverflow.com/a/48133859/1180974 . Google Drive just changed the API.

I'm having the same problems with Monterrey. Not working!

Thanks, @Shubhamjain27! What version of ShapeNet did you use to train DIB-R? If I use ShapeNetCore.v2 I'm missing the models (I only find normalized models) and the renders. If you...