用多缓冲机制提升神经场渲染质量，插件式设计兼容主流方法
K-Buffers: A Plug-in Method for Enhancing Neural Fields with Multiple Buffers
- 通过生成多个像素级特征缓冲区，融合多视角信息增强细节
- 在神经点场和3DGS上实现更清晰的图像输出，视觉质量显著提升
- 可插拔部署，适合需要高质量实时渲染的研究与应用
神经场已成为3D视觉与计算机图形学的研究核心。现有方法主要关注场景表示形式，如神经点和3D高斯。然而，较少研究聚焦于渲染过程本身以提升神经场性能。本文提出一种名为K-Buffers的插件式方法，利用多个缓冲区来改进渲染效果。首先从场景表示中渲染出K个缓冲区，并构建K个像素级特征图；随后引入K-特征融合网络（KFN）合并这些特征图；最后通过特征解码器生成渲染图像。我们还设计了一种加速策略，进一步提升渲染速度与质量。该方法已应用于知名辐射场基线模型，包括神经点场和3D高斯泼溅（3DGS）。大量实验表明，该方法能有效提升神经点场与3DGS的渲染表现。
原文摘要 · Abstract (English)
Neural fields are now the central focus of research in 3D vision and computer graphics. Existing methods mainly focus on various scene representations, such as neural points and 3D Gaussians. However, few works have studied the rendering process to enhance the neural fields. In this work, we propose a plug-in method named K-Buffers that leverages multiple buffers to improve the rendering performance. Our method first renders K buffers from scene representations and constructs K pixel-wise feature maps. Then, We introduce a K-Feature Fusion Network (KFN) to merge the K pixel-wise feature maps. Finally, we adopt a feature decoder to generate the rendering image. We also introduce an acceleration strategy to improve rendering speed and quality. We apply our method to well-known radiance field baselines, including neural point fields and 3D Gaussian Splatting (3DGS). Extensive experiments demonstrate that our method effectively enhances the rendering performance of neural point fields and 3DGS.
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。