Get 3D scene using Gaussian splatting with normal, depth maps, and geometric constraints with PGSR
Get 3D scene using Gaussian splatting with normal, depth maps, and geometric constraints with PGSR
PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction
arXiv paper abstract https://arxiv.org/abs/2406.06521
arXiv PDF paper https://arxiv.org/pdf/2406.06521
Project page https://zju3dv.github.io/pgsr
... 3D Gaussian Splatting (3DGS) ... is difficult to guarantee geometric reconstruction accuracy and multi-view consistency simply by relying on image reconstruction loss.
... propose a fast planar-based Gaussian splatting reconstruction representation (PGSR) to achieve high-fidelity surface reconstruction while ensuring high-quality rendering.
... introduce an unbiased depth rendering ... which ... renders the distance from the camera origin to the Gaussian plane and the corresponding normal map based on the Gaussian distribution of the point cloud, and divides the two to obtain the unbiased depth.
... then introduce single-view geometric, multi-view photometric, and geometric regularization to preserve global geometric accuracy.
... also propose a camera exposure compensation model to cope with scenes with large illumination variations.
... method achieves fast training and rendering while maintaining high-fidelity rendering and geometric reconstruction, outperforming 3DGS-based and NeRF-based methods.
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