Kai-46 / ARF-svox2

Artistic Radiance Fields
BSD 2-Clause "Simplified" License
510 stars 42 forks source link

Using my own dataset #7

Closed LiquidAmmonia closed 2 years ago

LiquidAmmonia commented 2 years ago

Hi there, I have been trying to use your work on my own dataset, I managed to get the colmap results and finished the voxel optimization process. However, I come across "AttributeError: 'NSVFDataset' object has no attribute 'render_c2w'" Error when rendering results using render_imgs.py. It seemed that the code automatically identify my dataset as a 'NSVFDataset' instead of a 'LLFFDataset'. Could you tell me how to solve this bug?

My dataset looks like this after the dataset generation process provided in svox2. image

LiquidAmmonia commented 2 years ago

This bug only occurs when using "--render_path" argument. The testing with metrics works fine.

Kai-46 commented 2 years ago

Did you use this try_llff.sh script: https://github.com/Kai-46/ARF-svox2/blob/22baf6e000e519b21ca26308f8ead1f4d2675cf5/opt/try_llff.sh#L4?

LiquidAmmonia commented 2 years ago

I did, but the custom dataset does not have 'pose_bounds.npy', so the dataset is extended to NSVF Dataset according to opt/util/dataset.py

Kai-46 commented 2 years ago

You can use this script to generate the pose_bounds.npy file, I think: https://github.com/Fyusion/LLFF/blob/master/imgs2poses.py