Cannot reproduce the results on LLFF dataset

[cwchenwang]

Hi, I used your code in render.ipynb and tried to evaluate the pretrained model on LLFF, but I found the metrics are significant lower than that reported in the paper, for example: for the room scene, the result PSNR are only 22.99, but in the paper it is 26.95.

[shangqideng]

Hi, I used your code in render.ipynb and tried to evaluate the pretrained model on LLFF, but I found the metrics are significant lower than that reported in the paper, for example: for the room scene, the result PSNR are only 22.99, but in the paper it is 26.95.

May I ask which dataset you used for pretraining

[cwchenwang]

Hi, I used your code in render.ipynb and tried to evaluate the pretrained model on LLFF, but I found the metrics are significant lower than that reported in the paper, for example: for the room scene, the result PSNR are only 22.99, but in the paper it is 26.95.

May I ask which dataset you used for pretraining

I used the provided checkpoints, but the problem is solved now by changing the configs.

[stevehan00]

@cwchenwang Hi, I faced with the same problem. Can I ask you for modified configs?