Cannot reproduce NeRF results on LLFF Fern dataset

[sergeyprokudin]

Hi Pytorch3d team,

I was recently trying to reproduce the results of Pytroch3d NeRF implementation on the LLFF "fern" dataset. No changes on my side were made to the code, I've just run the provided command:

python ./train_nerf.py --config-name fern

However, the results I'm getting on the validation set are significantly lower than the ones reported in the readme (27.9 PSNR vs 17.8 I'm getting). I somehow feel this might be connected to the behavior described in the following open issue.

It would be great if you can look into this. Having reproducible NeRF baselines in a modular and extendable framework like Pytorch3d would be of great help for future research on neural rendering.

Thanks in advance,

~Sergey

[gkioxari]

It's my understanding that we are deprecating projects/nerf with the new implicitron library

[sergeyprokudin]

I see, thanks for the clarification! It would be great to have the code for reproducing NeRF LLFF and Lego within the implicitron framework then.

[gkioxari]

@bottler @davnov134 Can you point Sergey to the code that reproduces NeRF for LLFF and Lego?

[sergeyprokudin]

Hi folks! Any update on this?

[weizhenFrank]

@sergeyprokudin Bro, I also have the same problem as you. I run the code
python ./train_nerf.py --config-name fern and python ./test_nerf.py --config-name fern. But I didn't fully reproduce the result. My result is as the screenshot shows.

However, the repo here said the PSNR should be

| Implementation |  Lego: test PSNR |  Fern: test PSNR |  training speed |
+----------------+------------------+------------------+-----------------+
| TF (official)  |             31.0 |             27.5 |  0.24 sec/it    |
| PyTorch3D      |             32.7 |             27.9 |  0.18 sec/it    |
+----------------+------------------+------------------+-----------------+```

[weizhenFrank]

Update: Just as #868 said, this implementation has some problems for non-square images. But I successfully reproduce the lego result.