Open tangfucius opened 1 week ago
Your iphone results doesn't look right to me. If you can share cameras.bin + images.bin + points3D.bin + images folder
, I might be able to debug a bit.
Thanks for your response! I uploaded them here.
Is there anything else you'd suggest me to look at on my side? Bottom line, given the same inputs, do we expect the quality of Splatfacto
to be similar to other implementations?
Hello @tangfucius , it is not fair comparison since splatfacto uses some images for eval dataset and not all images trained.
You can maximize the power of Splatfacto by using all images for training.
Try to add --eval-mode fraction --train-split-fraction 1
flags.
For example:
ns-train splatfacto-big nerfstudio-data --data path/to/dataset --eval-mode fraction --train-split-fraction 1
TL;DR I compared the splats of a room generated by Splatfacto and Postshot with the same inputs, and consistently found Postshot to be crisper.
Do we already know if some components (ns-process-data or Splatfacto algorithm) are suboptimal, particularly regarding how
ns-process-data
uses colmap outputs?Set up Inputs (for the same room):
Both Nerfstudio and Postshot were run on Windows.
Nerfstudio I used
ns-process-data video/images
to generate inputs for training.transforms.json
contains 342 frames.transforms.json
only contains 25 frames (out of 56), even if I used--matching-method exhaustive
.Postshot I tried these 2 settings:
Use Best Images
for image selection)cameras.bin + images.bin + points3D.bin + images folder
generated fromns-process-data
aboveDefault settings were used for training (Splat MCMC). Subjectively, I found the splat quality of these 2 settings to be pretty similar.
Results Postshot tend to have crisper results for all cases. All renders are 1920 x 1080.
iPhone Nerfstudio Postshot (direct import) Postshot (colmap)
android Nerfstudio Postshot (direct import) Postshot (colmap)
Questions As a supporter of open source, I'd love to see Nerfstudio match the quality of Postshot. Asking these questions to better understand where I can possibly contribute:
*.bin
files) as Nerfstudio (transforms.json
). Why is that the case?hcol
perform better thancolmap
forns-process-data
? Tried using it but haven't managed to get thepycolmap
dependency to install on Windows so far.