Projecting Gaussian Ellipsoids While Avoiding Affine Projection Approximation
Han Qi, Tao Cai, Xiyue Han

TL;DR
This paper introduces an ellipsoid-based projection method for 3D Gaussian Splatting that reduces errors caused by affine projection approximations, improving rendering quality and scene consistency.
Contribution
The authors propose a novel ellipsoid-based projection technique that avoids affine projection errors in 3D Gaussian Splatting, with a pre-filtering strategy for challenging cases.
Findings
Enhanced rendering quality on benchmark datasets
Reduced artifacts and blurriness in synthesized views
Improved scene consistency in 3D Gaussian Splatting
Abstract
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 plane in the camera space, we designed a pre-filtering strategy. Experiments over multiple widely adopted benchmark datasets show that our ellipsoid-based projection…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsStatistical and numerical algorithms · Advanced Numerical Analysis Techniques
MethodsSPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
