Elastic Triangle Splatting
Computer Vision and Pattern RecognitionComputational Geometry
Summary
The authors studied a method called triangle splatting, which helps blend neural rendering techniques with traditional 3D mesh workflows by treating triangles as soft, adjustable shapes for optimization. They analyzed different functions that control how these triangles spread their influence, called kernels, to see which work best for improving 3D shapes and views. They introduced a new 'elastic kernel' that better supports changes at triangle edges, leading to more reliable optimization results. Their experiments showed this new kernel often outperforms others in both reconstructing shapes and synthesizing new views. This work highlights how the choice of kernel function is important for making triangle splatting effective and flexible.
Authors
Tian Shi, Shenhan Qian, Daniel Cremers
Abstract
While neural rendering methods such as 3D Gaussian Splatting achieve remarkable visual fidelity, traditional polygonal meshes remain the backbone of established graphics pipelines. Triangle splatting bridges this gap by optimizing triangle primitives as differentiable splats, producing representations that are closer to mesh-based workflows. Central to these methods is the kernel function that softens triangle boundaries to propagate gradients to vertex positions. Existing triangle splatting methods make inconsistent choices of kernel functions, and analysis of these kernels' optimization behavior has been limited to unstructured triangle soups for novel-view synthesis. In this work, we consider triangle splatting as a generic tool for photometric optimization, comparing kernel properties through two complementary tasks: mesh optimization for shape reconstruction and triangle soup optimization for novel-view synthesis. Along with the analysis, we introduce an elastic kernel function that features bilateral gradient support across the boundary and an adaptive boundary value, which are shown to be essential for robust optimization. Under isolated comparison, our elastic kernel outperforms existing kernels on shape reconstruction and in the majority of novel-view synthesis benchmarks, demonstrating the importance of kernel design in the effectiveness and versatility of triangle splatting.