无需网格，通过调整3D高斯点云参数实现真实感数据增强
Meshless Domain Randomization via Explicit Parameter Perturbation of 3D Gaussian Splatting
- 直接在3D高斯点云参数空间进行光照与纹理扰动
- 生成带随机背景的合成数据，提升模型泛化能力
- 适合复杂有机体如昆虫的仿真到真实迁移
领域随机化（DR）是缩小仿真到现实差距的标准方法，但传统流程依赖基于多边形网格的计算机图形渲染。对于昆虫等复杂有机体，提取并渲染带纹理的网格极具挑战。为此，我们提出一种基于3D高斯点云（3DGS）参数空间的无网格DR框架。该方法采用两个独立扰动管道：首先，光照域随机化通过调节球谐函数（SH）系数改变烘焙光照与色彩平衡；其次，程序化域随机化通过用三维空间噪声替换原始纹理，分离出物体几何形状。最后，利用光栅化引擎将扰动后的辐射场与随机变化的背景合成。该参数操控方法为复杂几何体提供了无网格的数据增强方案。
原文摘要 · Abstract (English)
Domain Randomization (DR) is a standard technique for closing the Sim-to-Real gap, yet traditional DR pipelines rely on classical computer graphics rendering driven by polygon meshes. For complex organic subjects, such as insect specimens, extracting and rendering textured meshes is challenging. To address this issue, we propose a meshless DR framework that operates on the parameter space of 3D Gaussian Splatting (3DGS). Our method employs two independent perturbation pipelines to synthesize randomized training datasets. First, a Photometric DR pipeline alters the baked illumination and color balance by modulating the Spherical Harmonics (SH) coefficients. Second, a Procedural DR pipeline isolates the subject's geometric shape by replacing its original textures with 3D spatial noise. Finally, these perturbed radiance fields are composited over stochastically varied backgrounds using a rasterization engine. Our parameter manipulation provides a meshless alternative for generating robust datasets for complex geometries.
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。