Get 3D scene using SDF to guide the densify and prune of Gaussians with GaussianRoom
Get 3D scene using SDF to guide the densify and prune of Gaussians with GaussianRoom
GaussianRoom: Improving 3D Gaussian Splatting with SDF Guidance and Monocular Cues for Indoor Scene Reconstruction
arXiv paper abstract https://arxiv.org/abs/2405.19671
arXiv PDF paper https://arxiv.org/pdf/2405.19671
Project page https://xhd0612.github.io/GaussianRoom.github.io
... 3D Gaussian Splatting(3DGS) ... when ... indoor scenes with ... textureless areas, 3DGS yields incomplete and noisy reconstruction ... due to the poor initialization of the point cloud and under-constrained optimization.
Inspired by the continuity of signed distance field (SDF), which ... has advantages in modeling surfaces, ... present a unified optimizing framework integrating neural SDF with 3DGS.
This framework incorporates a learnable neural SDF field to guide the densification and pruning of Gaussians, enabling Gaussians to accurately model scenes even with poor initialized point clouds.
At the same time, the geometry represented by Gaussians improves the efficiency of the SDF field by piloting its point sampling.
Additionally, ... regularize the optimization with normal and edge priors to eliminate geometry ambiguity in textureless areas and improve the details.
... method achieves state-of-the-art performance in both surface reconstruction and novel view synthesis.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments