让点云渲染的模糊效果自动适应视角，提升3D新视图生成质量。
Learning View-Dependent Splatting Kernels
- 用可微分网络学习随视角变化的2D核函数
- 在标准数据集上优于现有分析与学习型核方法
- 适用于3D点云渲染和2D图像表示任务
我们提出一种可微分框架，用于在基于点绘制（splatting）的流水线中自动学习视图依赖的2D核函数，以提升3D新视图合成的重建质量和表示效率。我们的体素原语定义为一个边界椭球和一个3D核隐向量。首先，通过一个投影网络输出2D核隐向量，输入为椭球属性和3D核隐向量；随后，该结果送入解码器，生成以马氏距离为基准的径向对称2D核，其范围由投影后的椭球限定。神经网络与每个原语的属性联合优化。在标准基准上的实验表明，该方法在分析核和学习核两种设定下均优于当前最优技术。最后，我们将该思想扩展至学习通用2D核，应用于2D点绘制及图像表示。
原文摘要 · Abstract (English)
We present a differentiable framework to automatically learn view-dependent 2D kernels in a splatting-based pipeline to improve reconstruction quality and representation efficiency for novel 3D view synthesis. Our volumetric primitive is defined as a bounding ellipsoid and a 3D-kernel latent vector. We first learn a projection network to output a 2D-kernel latent, taking the attributes of the ellipsoid and the 3D-kernel latent as input. Next, the result is sent to a decoder to produce a radially symmetric 2D kernel in terms of Mahalanobis distance, bounded by the projected ellipsoid. The neural networks along with per-primitive attributes are jointly optimized. The effectiveness of our approach is demonstrated on standard benchmarks, comparing favorably against state-of-the-art techniques on both analytical and learned kernels. Finally, we extend the idea to learn general 2D kernels for 2D splatting as well as image 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。