BrepGaussian：基于高斯泼溅的多视图图像 CAD 重建
BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splatting
把高斯泼溅渲染器改造成带可学习特征的 B-Rep 参数化曲面拟合器，使视觉研究者可以直接从多视图图像回归 CAD 边界表示，绕开对稠密干净点云的依赖；其两阶段解耦（先几何与边、后图像块特征精修）思路可迁移到其他需要从渲染监督中分离几何与语义特征的逆渲染任务。
原文依据 We employ a Gaussian Splatting renderer with learnable features, followed by a specific fitting strategy.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论边界表示（B-Rep）以显式边界——裁剪角点、边与面——来建模三维实体。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一项具有挑战性且有价值的任务。深度学习的最新进展大幅提升了三维形状几何的恢复能力，但仍依赖稠密且干净的点云，并且难以泛化到新形状。我们提出 B-Rep 高斯泼溅（BrepGaussian），一个从二维图像学习三维参数化表示的新框架。我们采用带可学习特征的高斯泼溅渲染器，并配合特定的拟合策略。为解耦几何重建与特征学习，我们引入两阶段学习框架：先捕获几何与边，再精修图像块特征，从而获得干净的几何与一致的实例表示。大量实验表明，我们的方法优于最优方法。
英文原文摘要 1001 字符
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.