用6维方向感知高斯点提升实时三维渲染质量
6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering
- 引入6维空间增强方向感知，优化颜色与透明度表示
- 比3DGS减少66.5%点数，PSNR最高提升15.73 dB
- 适合追求高质量实时渲染的图形开发与视觉生成研究者
新视角合成因神经辐射场（NeRF）和3D高斯溅射（3DGS）的发展取得显著进展。然而，在保持实时渲染的前提下实现高质量渲染仍具挑战性，尤其在包含视角依赖效应的物理级光线追踪场景中。近期提出的N维高斯（N-DG）采用6维空间-角度表示以更好地建模视角依赖效应，但其高斯表示与控制机制仍不理想。本文重新审视6维高斯，提出6维高斯溅射（6DGS），通过增强颜色与透明度表示，并利用6维空间中的额外方向信息优化高斯控制。该方法完全兼容3DGS框架，显著提升实时辐射场渲染效果，更精准建模视角依赖效应与精细细节。实验表明，6DGS显著优于3DGS与N-DG，相比3DGS减少66.5%高斯点数的同时，PSNR最高提升15.73 dB。
原文摘要 · Abstract (English)
Novel view synthesis has advanced significantly with the development of neural radiance fields (NeRF) and 3D Gaussian splatting (3DGS). However, achieving high quality without compromising real-time rendering remains challenging, particularly for physically-based ray tracing with view-dependent effects. Recently, N-dimensional Gaussians (N-DG) introduced a 6D spatial-angular representation to better incorporate view-dependent effects, but the Gaussian representation and control scheme are sub-optimal. In this paper, we revisit 6D Gaussians and introduce 6D Gaussian Splatting (6DGS), which enhances color and opacity representations and leverages the additional directional information in the 6D space for optimized Gaussian control. Our approach is fully compatible with the 3DGS framework and significantly improves real-time radiance field rendering by better modeling view-dependent effects and fine details. Experiments demonstrate that 6DGS significantly outperforms 3DGS and N-DG, achieving up to a 15.73 dB improvement in PSNR with a reduction of 66.5% Gaussian points compared to 3DGS. The project page is: https://gaozhongpai.github.io/6dgs/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。