用少量三角形和神经纹理实现可微渲染，支持低配设备实时交互。
DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification
- 用少量无序三角形加神经纹理构建可微辐射场。
- 通过随机透明度掩码实现直接可微，无需平滑处理。
- 兼容传统渲染管线，可在普通笔记本上实时运行。
辐射场重建旨在从多视角RGB图像中恢复高质量3D表示。近年来，如3D高斯溅射等方法可在高性能显卡上实现实时高保真渲染。然而，为实现跨平台高效在线传输与渲染，需将原始模型简化数个数量级，大幅减少基础图元数量。本文提出DiffSoup，一种采用少量三角形（即非结构化集合）的辐射场表示，结合神经纹理与二值不透明度。我们证明该二值不透明度可通过随机不透明度掩码实现直接可微，从而在无需光滑器（即平滑光栅化）的情况下实现稳定训练。DiffSoup可利用标准深度测试进行光栅化，实现与传统图形管线无缝集成，并支持在消费级笔记本及移动设备上的交互式渲染。代码已公开于https://github.com/kenji-tojo/diffsoup。
原文摘要 · Abstract (English)
Radiance field reconstruction aims to recover high-quality 3D representations from multi-view RGB images. Recent advances, such as 3D Gaussian splatting, enable real-time rendering with high visual fidelity on sufficiently powerful graphics hardware. However, efficient online transmission and rendering across diverse platforms requires drastic model simplification, reducing the number of primitives by several orders of magnitude. We introduce DiffSoup, a radiance field representation that employs a soup (i.e., a highly unstructured set) of a small number of triangles with neural textures and binary opacity. We show that this binary opacity representation is directly differentiable via stochastic opacity masking, enabling stable training without a mollifier (i.e., smooth rasterization). DiffSoup can be rasterized using standard depth testing, enabling seamless integration into traditional graphics pipelines and interactive rendering on consumer-grade laptops and mobile devices. Code is available at https://github.com/kenji-tojo/diffsoup.
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。