从多视角图像重建精确的3D CAD模型，用高斯点云实现细节还原。
BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splatting
- 基于可学习特征的高斯渲染，从2D图像生成3D参数化表示
- 两阶段训练：先恢复几何结构与边缘，再优化表面特征
- 在新形状上表现更优，适合工业级3D建模场景
边界表示（B-Rep）将三维实体显式建模为裁剪后的角、边和面。从非结构化数据中恢复B-Rep表示是计算机视觉与图形学中的挑战性且有价值的任务。近年来深度学习显著提升了3D形状几何恢复能力，但仍依赖密集且干净的点云，且对新形状泛化能力不足。我们提出B-Rep高斯点云（BrepGaussian），一种从2D图像学习3D参数化表示的新框架。采用带有可学习特征的高斯点云渲染器，并结合特定拟合策略。为解耦几何重建与特征学习，引入两阶段学习框架：先捕捉几何与边缘，再精细化修补特征以获得清晰几何与一致实例表示。大量实验表明，本方法优于现有最先进方法。
原文摘要 · Abstract (English)
The boundary representation (B-Rep) models a 3D solid as its explicit boundaries: trimmed corners, edges, and faces. Recovering B-Rep representation from unstructured data is a challenging and valuable task of computer vision and graphics. Recent advances in deep learning have greatly improved the recovery of 3D shape geometry, but still depend on dense and clean point clouds and struggle to generalize to novel shapes. We propose B-Rep Gaussian Splatting (BrepGaussian), a novel framework that learns 3D parametric representations from 2D images. We employ a Gaussian Splatting renderer with learnable features, followed by a specific fitting strategy. To disentangle geometry reconstruction and feature learning, we introduce a two-stage learning framework that first captures geometry and edges and then refines patch features to achieve clean geometry and coherent instance representations. Extensive experiments demonstrate the superior performance of our approach to state-of-the-art methods.
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。