search

city-super / Scaffold-GS

[CVPR 2024 Highlight] Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering
https://city-super.github.io/scaffold-gs
Other
772 stars 67 forks source link

positional encoding #27

Open Torment123 opened 8 months ago

Torment123 commented 8 months ago

Hi, thanks for the great work and congrats for CVPR acceptance. I saw in the code that ob_dist and ob_view are directly concatenated with anchor feature and input to the MLPs. Would using positional encoding (like in NeRF) further improve the view-dependent appearance rendering? as it captures high frequency variations, thanks.

inspirelt commented 8 months ago

Thanks. We choose direct concatenation because 1) reducing the total computation; 2) we find that a naive PE does not always contribute to a better results. Further explorations are welcome.