用NeRF提升3D高斯泼溅的精度与稳定性。
NeRF Is a Valuable Assistant for 3D Gaussian Splatting
- 联合优化NeRF与3D高斯泼溅，共享空间信息。
- 在多个基准数据集上达到顶尖性能。
- 适合追求高质量3D重建的研究者。
我们提出NeRF-GS，一种联合优化神经辐射场（NeRF）与3D高斯泼溅（3DGS）的新框架。该框架利用NeRF的连续空间表示，缓解3DGS对高斯初始化敏感、空间感知弱及高斯间关联性差等问题，从而提升其性能。在NeRF-GS中，我们重新设计3DGS结构，逐步将其空间特征对齐至NeRF，使两者基于共享的3D空间信息共同优化。通过为隐式特征和高斯位置优化残差向量，进一步增强3DGS的个性化能力。在多个基准数据集上的实验表明，NeRF-GS超越现有方法，达到当前最优性能。结果证实，NeRF与3DGS是互补而非竞争关系，为高效3D场景表示提供了混合建模新思路。
原文摘要 · Abstract (English)
We introduce NeRF-GS, a novel framework that jointly optimizes Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). This framework leverages the inherent continuous spatial representation of NeRF to mitigate several limitations of 3DGS, including sensitivity to Gaussian initialization, limited spatial awareness, and weak inter-Gaussian correlations, thereby enhancing its performance. In NeRF-GS, we revisit the design of 3DGS and progressively align its spatial features with NeRF, enabling both representations to be optimized within the same scene through shared 3D spatial information. We further address the formal distinctions between the two approaches by optimizing residual vectors for both implicit features and Gaussian positions to enhance the personalized capabilities of 3DGS. Experimental results on benchmark datasets show that NeRF-GS surpasses existing methods and achieves state-of-the-art performance. This outcome confirms that NeRF and 3DGS are complementary rather than competing, offering new insights into hybrid approaches that combine 3DGS and NeRF for efficient 3D scene representation.
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。