DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification
For applications requiring efficient online transmission and rendering of 3D scenes across diverse platforms, DiffSoup provides a method to drastically simplify radiance fields while retaining quality and enabling real-time rendering on low-power devices.
DiffSoup introduces a radiance field representation using a small set of triangles with neural textures and binary opacity, enabling drastic model simplification (reducing primitives by orders of magnitude) while maintaining high visual fidelity. It achieves interactive rendering on consumer-grade laptops and mobile devices.
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.