3D Skew Gaussian Splatting with Any Camera Trajectory Visualization Engine

2026-05-18

AI Summary

This work addresses the limitations of conventional 3D Gaussian Splatting (3DGS), which employs symmetric Gaussians and consequently suffers from blurring and redundancy in regions with shape or color discontinuities, hindering precise spatial visualization. To overcome this, we propose the 3D Skewed Gaussian Splatting (3DSGS) framework, which introduces skewed Gaussian primitives into 3DGS for the first time, endowing it with intrinsic asymmetric modeling capability. The approach further integrates an enhanced opacity formulation and a depth-aware densification strategy to improve structural fidelity and compactness of scene representation. Implemented via a re-engineered CUDA rasterization pipeline and a decoupled free-camera rendering engine, our system significantly enhances rendering quality in complex, detailed regions while maintaining real-time frame rates, enabling efficient interactive exploration along arbitrary camera trajectories.

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 this with an enhanced opacity representation to better handle complex transparency, alongside a depth-aware densification strategy that intelligently manages primitive allocation. Furthermore, to make these advancements actionable for real-world visual analytics, we re-derive the CUDA rasterization pipeline to universally support both symmetric and skew Gaussians, integrating it into a decoupled, free-camera interactive visualization engine. Extensive experiments demonstrate that 3DSGS achieves superior rendering quality and structural compactness, particularly in regions with intricate details, while maintaining the real-time frame rates necessary for fluid interactive exploration. Supplementary derivations and visual results are available at \textbf{\textit{https://3d-skew-gs.github.io/}}.

Problem

• 3D Gaussian Splatting
• visual artifacts
• shape discontinuities
• color discontinuities
• spatial data exploration

Innovation

• Skew Gaussian
• 3D Gaussian Splatting
• asymmetric modeling
• real-time rendering
• interactive visualization