Yan Zhiwen
Yan Zhiwen
Agreed. The lpips metric in eval.py seems wrong
No, I didn't. I think that is the problem. Thank you very much!
Thank you very much for the reply. I think the issue mentioned [here](https://www.nerfacc.com/en/stable/methodology/coding.html#profiling) is very much aligned with my observation. The masking without indices does take a lot of time...
Thank you very much for the detailed explanation. It does explain the wired time I have observed. Good work on the nerfacc repo. I have been trying to optimize the...
I am using the ngp version of the nerfacc. I was timing the traverse_grid and skip_invisible separately. If my understanding is correct, the traverse_grid does not evaluate the radiance field,...
Sorry that I am now busy with the NeurIPS deadline. I will see whether I can provide you with the test cases I used after the ddl. However, I am...
I have uploaded the parameters used for sampling in NerfAcc and Plenoxels [here](https://drive.google.com/drive/folders/1ZNMPKacZtcPi-ZerqpMMH8mFdQ_B9dQl?usp=sharing). For NerfAcc, I am calling `traverse_grids` with all the parameters provided in the pkl. For Plenoxel, the...
May I confirm that the pretrained model used for both pilot and full model training are referring to the first frame model?
Thank you very much for the plan of releasing such a guide. May I ask whether you can include the instructions to run the "compositional ENeRF" in the guide as...
I have exactly the same issue. Everything is standard but the result is very bad