Projecting Gaussian Ellipsoids While Avoiding Affine Projection Approximation
This work addresses rendering quality issues in novel-view synthesis for computer vision and graphics applications, representing an incremental improvement over existing 3D Gaussian Splatting methods.
The paper tackles the problem of blurriness and artifacts in 3D Gaussian Splatting rendering caused by affine projection approximation errors, and introduces an ellipsoid-based projection method that enhances rendering quality across multiple benchmark datasets.
Recently, 3D Gaussian Splatting has dominated novel-view synthesis with its real-time rendering speed and state-of-the-art rendering quality. However, during the rendering process, the use of the Jacobian of the affine approximation of the projection transformation leads to inevitable errors, resulting in blurriness, artifacts and a lack of scene consistency in the final rendered images. To address this issue, we introduce an ellipsoid-based projection method to calculate the projection of Gaussian ellipsoid onto the image plane, which is the primitive of 3D Gaussian Splatting. As our proposed ellipsoid-based projection method cannot handle Gaussian ellipsoids with camera origins inside them or parts lying below $z=0$ plane in the camera space, we designed a pre-filtering strategy. Experiments over multiple widely adopted benchmark datasets show that our ellipsoid-based projection method can enhance the rendering quality of 3D Gaussian Splatting and its extensions.