TL;DR
This paper introduces 3D Skew Gaussian Splatting (3DSGS), a novel visualization framework that enhances 3D scene representation fidelity and compactness by extending Gaussian primitives to asymmetric Skew Gaussians, enabling better detail capture and real-time rendering.
Contribution
The authors propose a new Skew Gaussian primitive and an optimized CUDA rasterization pipeline, improving 3D visualization quality and efficiency over traditional symmetric Gaussian methods.
Findings
3DSGS achieves higher structural fidelity in complex regions.
It maintains real-time rendering performance.
Enhanced transparency handling improves visual clarity.
Abstract
While 3D Gaussian Splatting (3DGS) has revolutionized real-time photorealistic view synthesis, its fundamental reliance on symmetric Gaussian distributions introduces visual artifacts that hinder accurate spatial data exploration. Specifically, symmetric kernels struggle to capture shape and color discontinuities , which cause blurriness and primitive redundancy that mislead human perception during visual analysis. To address these visualization barriers, we introduce 3D Skew Gaussian Splatting (3DSGS), a novel framework that significantly enhances the structural fidelity and compactness of explicit scene representations. Our key insight lies in extending the standard primitive to a general Skew Gaussian counterpart. This generalized primitive inherits the highly efficient rasterization properties of standard Gaussians while gaining intrinsic asymmetric modeling capabilities. We couple…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
