BrepGaussian: CAD reconstruction from Multi-View Images with Gaussian Splatting

TL;DR

This work proposes B-rep Gaussian Splatting (BrepGaussian), a novel framework that learns 3D parametric representations from 2D images that first captures geometry and edges and then refines patch features to achieve clean geometry and coherent instance representations.

Abstract

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. We will release our code and datasets upon acceptance.

Figures (7)

• Figure 1: Given multi-view images, our pipeline reconstructs a CAD model through feature-aware Gaussian Splatting and parametric surface fitting. The Gaussian Splatting framework produces the geometric point cloud with edge and patch labels, which enables us to reconstruct parametric primitives from patch labels and extract lines and curves with the guidance of edge points.
• Figure 2: Overall pipeline of BrepGaussian. Given multi-view RGB images of a CAD object, we extract edge and patch views using existing edge detection and segmentation models. These views drive a two-stage Gaussian Splatting model that predicts edge and patch labels on the reconstructed point cloud. The fitted primitives are globally optimized to obtain the final B-rep model.
• Figure 3: Illustration of optimized 2D Gaussians. flat regions use fewer nearly spherical Gaussians, while edge regions require more elongated Gaussians.
• Figure 4: Qualitative comparison on patch segmentation. Our BrepGaussian produces cleaner and more consistent patch segmentation.
• Figure 5: Qualitative comparison on CAD reconstruction. Our BrepGaussian exhibit more accurate geometry.