Wenyuan Zhang

> I have met the same problem mentioned here, and the solution I took is to reinstall the pytorch and downgrade to `1.4` version with consistent cuda version 10.0 (as...

> Hello I got a similar error. The reason why I met the error is, the image_id in Database Table of images in 'database.db' does not perfectly ordered in image...

I will later try it. Thanks for your reply!

Just for reference: I use the pose of the replica dataset to obtain the correct results without any transformation. 

Thanks for the great work @yashbhalgat , do you now have any idea about the performance (numerical results) gap between instant and this implementation? I guess there may be some...

> train.py in nerfstudio/scripts/train.py is equivalent to ns-train. You can just replace everything ns-train with a call to that file. I successfully debugged locally. Additionally, do not install nerfstudio, otherwise...

@anas-zafar yeah. I debugged it in pycharm and it worked normally.

In linux command line, train with "CUDA_VISIBLE_DEVICES=2,3 python ddp_train_nerf.py xxxxxx "

I later found there is no problem in the rendering script. The problem is that tsdf fuison results in the reconstructed mesh a little thicker. However, the rendered depth map...

Thanks for your reply! Following your advice, I find that nerfstudio reimplemented instant-ngp using pytorch which may be helpful. I'll keep an eye on this problem. Thanks again!