We introduce Scaffold-GS, which uses anchor points to distribute local 3D Gaussians, and predicts their attributes on-the-fly based on viewing direction and distance within the view frustum.
[Project Page][arxiv]
Our method performs superior on scenes with challenging observing views. e.g. transparency, specularity, reflection, texture-less regions and fine-scale details.
The code is estimated to be released in this week~