nerf-pytorch

nerf-pytorch copied to clipboard

I meet some question when I use my own datasets. When I put the poses_bounds.npy from the imgs2poses into the nerf, the results of rendering are very bad, and the...

shangqideng

Sorry，your nerf is implemented by pytorch, but the llff is still tf?

lemonsstyle

Problems with models .tar

1

Hi. When I tried to untar the file 200000.tar in a terminal of ubuntu from (lego_test at https://drive.google.com/drive/folders/1jIr8dkvefrQmv737fFm2isiT6tqpbTbv) I receive these bugs: ``` >tar -xvf 200000.tar tar: This does not...

jdiazram

Which version of Python should be used

1

joselynzhao

Get poses from ARkit data

1

Hi, All works fine via LLFF(COLMAP), but I have extrinsic data (quaternions and translation) from ARkit. But if simply pass my own quaternions and translation vector instead COLMAPs into img2poses...

Vadkoz

This line was mentioned by Xiangjun-Gao on 28 Jan 2021 (https://github.com/yenchenlin/nerf-pytorch/issues/22 ), but I find it has not been fixed yet.

wyf2020

Hi, Thank you for the great work. I applied NeRF to my datasets that was obtained through the [ios_logger app](https://github.com/Varvrar/ios_logger/). [This](https://github.com/hyunJIN7/nerf-pytorch/blob/master/load_arkit.py) is data loaging code. The following is the result...

hyunJIN7

Your work is excellent!I used fern data set to train the model, and can output 120 pictures with a resolution of 1500 * 700. Now I hope to output the...

bishengderen

How much memory is required to replicate the paper result?

7

I'm trying to replicate the nerf paper result using your code. I'm using the following config on the fern data: factor = 4 llffhold = 8 N_rand = 4096 N_samples...

dunbar12138

Hi Yen @yenchenlin , Thank you so much for your work in transporting **nerf** to PyTorch! I found a little confused when meet with the process in solving the `look-at...

tomguluson92