Richard Shaw

I think there is a mistake when using downsample in the your_own_data.py data loader. Shouldn't the principle point cx, cy should also be divided by self.downsample? https://github.com/apchenstu/TensoRF/blob/17deeedae5ab4106b30a3295709ec3a8a654c7b1/dataLoader/your_own_data.py#L48

Not getting correct outputs

47

Hi, thank you for the code. I followed your instructions and managed to train a model using the vanilla network. However, my test results are not correct. The room classification...

Bad results on NYU dataset

3

I am trying to use this code for simple inpainting on the NYU dataset. I am not getting very good results (see below for an example output after epoch 85)....

Hi, thanks for the great work! I'm trying to get a textured mesh from my nerfie capture but I'm confused about how the deformation field works. I can get a...

LLFF scenes and NDC coordinates?

5

Does this repo support NDC coordinates for frontal scenes like the LLFF dataset?

Unsharp mask and Intensity Rescaler during training?

2

Hi thanks for the great work! I was wondering, do you apply the unsharp mask filter and intensity rescaler during training?

Could you please explain the meaning of these baselines? What is the difference between 'ergb' and 'ergb0' ? And what does baseline=False mean?

Results on ENeRF-Outdoor dataset and poor quality depth

6

Hi, thanks for the great work! However, after running your training script (python train_net.py --cfg_file configs/enerf/enerf_outdoor/actor1.yaml) on Actor1 for 50 epochs, I am getting the following results. The results for...

scale_mat in preprocess.py

2

Hi thanks for the great work! How do you compute the scale_mat in preprocess.py? How can we change this for our own data? Thanks

I am getting noisy results, mainly at the edges of objects, as shown below. I am training a static scene and have tried both feature_type = "4d" and "3d". Do...