提升3D高斯点云对高频细节的表达能力，让渲染更清晰。
AH-GS: Augmented 3D Gaussian Splatting for High-Frequency Detail Representation
- 通过增强输入特征流形复杂度和引入特征图损失，优化高频率信息建模。
- 在15000次迭代内，渲染质量超越Scaffold-GS，尤其在MipNeRf360-garden数据集上表现突出。
- 适合需要精细几何与纹理重建的应用，如虚拟现实、数字孪生场景生成。
3D高斯点云（3D-GS）是一种新型场景表示与视图合成方法。尽管Scaffold-GS相比原始3D-GS实现了更高实时渲染质量，但其对精细结构的渲染极度依赖充足视角。神经网络的谱偏差导致Scaffold-GS对场景中高频信息感知与学习能力较差。本文提出通过增强输入特征的流形复杂度，并引入基于网络的特征图损失，以提升3D-GS模型的图像重建质量。我们提出AH-GS，使结构复杂区域中的3D高斯能获得更高频编码，从而更有效地学习场景高频信息。此外，引入高频强化损失进一步增强模型捕捉细节的能力。实验表明，该方法显著提升渲染保真度，在特定场景（如MipNeRf360-garden）下，仅用15,000次迭代即超越Scaffold-GS的渲染质量。
原文摘要 · Abstract (English)
The 3D Gaussian Splatting (3D-GS) is a novel method for scene representation and view synthesis. Although Scaffold-GS achieves higher quality real-time rendering compared to the original 3D-GS, its fine-grained rendering of the scene is extremely dependent on adequate viewing angles. The spectral bias of neural network learning results in Scaffold-GS's poor ability to perceive and learn high-frequency information in the scene. In this work, we propose enhancing the manifold complexity of input features and using network-based feature map loss to improve the image reconstruction quality of 3D-GS models. We introduce AH-GS, which enables 3D Gaussians in structurally complex regions to obtain higher-frequency encodings, allowing the model to more effectively learn the high-frequency information of the scene. Additionally, we incorporate high-frequency reinforce loss to further enhance the model's ability to capture detailed frequency information. Our result demonstrates that our model significantly improves rendering fidelity, and in specific scenarios (e.g., MipNeRf360-garden), our method exceeds the rendering quality of Scaffold-GS in just 15K iterations.
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。