TiNeuVox
TiNeuVox copied to clipboard
novel view generation issue. overfitting?
Hi,
Thank you for releasing the code. It is quite helpful to me.
I used my dataset which contains 140 iamges with different time stamps. But the images only from 14 training camera poses. Then I found the network can't generate good novel view images. I used the same dataset on D-nerf and it worked well. Are 14 training views too sparse for training the network? Have you found the same problem?
Thanks
Thanks for your attention! I have not yet met this problem. Could you show the failed generated images? Then I can better understand the problem.
Yes. I interpolated camera poses from pose1(the first image) to pose2(the second image). You can see that only trained poses can have a good render performance.
Have you solved this? I might have the same problem, but it makes no sense to me to not be able to generate novel views?
Hi @dsvilarkovic,
I haven't solved the problem. If you have any thoughts on this, please let me know.
I solved it by converting my llff format camera poses to nerf/blender .json format with the script I found in torch-ngp https://github.com/ashawkey/torch-ngp/blob/main/scripts/llff2nerf.py
@dsvilarkovic Thank you for your solution. It solved my problem (not perfect but at least make sense). But I still don't get it. What cause this difference?
To be honest, I do not know. \
OK, thanks.