Replies: 2 comments 1 reply
-
Hi there, the NeRF / NSVF / mip-NeRF codebases do not respect color spaces / pre-multiplied alpha correctly and hence their PSNR calculation behaves in non-intuitive ways. instant-ngp tries to be more principled about it, resulting in worse PSNR numbers by default, but you can revert to original NeRF's behavior with the The following command should let you reproduce the numbers from the paper: ./scripts/run.py --mode nerf --nerf_compatibility --scene lego/transforms_train.json --test_transforms lego/transforms_test.json PS: note that you can just pass |
Beta Was this translation helpful? Give feedback.
-
Thanks for the tip for passing only
also, to do a really "fair" comparison, I uncomment this line Line 180 in e4e0053 to make the background white instead of black. The PSNR is like what I showed in the issue, 35.72 (5m) and 35.79 (10m). Switching the background back to black makes the PSNR become 36.06 (higher than white background!?), so I guess black background + longer training will get to the number? However, since most previous methods measure PSNR with white background, I think it's worth noting this difference. Next, concerning the FPS, in the paper it says 60 FPS, but when I measure the time by enclosing this line of code Line 282 in e4e0053 and changing the Lines 239 to 241 in e4e0053 I get only 0.033s per frame, i.e ~30FPS. What are the other secrets to get to 60FPS? |
Beta Was this translation helpful? Give feedback.
-
Hi, I tried to reproduce paper result, but cannot get to the number reported. The following is how I did the experiment, could you tell me where I did wrong?
kwea123/ngp_pl#3 (comment)
Beta Was this translation helpful? Give feedback.
All reactions