Closed KelestZ closed 2 years ago
huh when i train lego from scratch i get good results:
you're using a pre-trained checkpoint? maybe the code and checkpoint diverged
you're using a pre-trained checkpoint? maybe the code and checkpoint diverged
No, I am training it from scratch. This seems weird when I got ok results on the other data.
On lego, my PSNR curve converges much slower than yours:
Are you sure you're using the correct Lego data? The truck seems to be in a different position than it is in the standard NeRF-synthetic dataset; perhaps somehow multiple Lego training sets got intermixed?
Are you sure you're using the correct Lego data? The truck seems to be in a different position than it is in the standard NeRF-synthetic dataset; perhaps somehow multiple Lego training sets got intermixed?
Thanks for the reminder. Fixed the issue and closed the question :)
Thanks for the amazing work. When I run the code on nerf_synthetic data (i.e., Lego), I couldn't get the same results as good as shown in the paper. I am showing a rendered LEGO result as below (right):
The PSNR I got is ~21 on lego. I believe I followed the instructions for the installation and running. The example command line is like:
I'm also repeating the experiments on other data. The Drum and the hotdog in Syn data and the fern in LLFF data seem fine. No idea about other data just yet. Some good examples I got:
![image](https://user-images.githubusercontent.com/27111467/147994344-52e13ca5-853b-45c9-bf80-547b6c943924.png)