UniBRep generates detailed 3D CAD models from single images
UniBRep: Learning Unified Geometry and Topology for Image-conditioned B-Rep Generation
Computer Vision and Pattern RecognitionGraphics
Summary
Creating accurate 3D CAD models from a single image is hard because the model must have the right shape and the correct connections between surfaces. The authors propose UniBRep, which first builds a shape with a mesh that guides how the surfaces connect. It then refines this into a full CAD representation with valid curves and faces using learned features. Their method improves accuracy and works well even for complex shapes and photos it was not trained on.
What this means in practice
- •For cad software developers: Generate precise CAD models directly from single images for use in design and engineering workflows without manual modeling.$Commercial implications: Enables automated shape reconstruction tools integrated into CAD software, saving designers time on complex model creation.
- •For 3d printing service providers: Produce valid 3D models from a photo-based input that can be reliably printed without topology errors.
Authors
Haiyang Ying, Allen Tu, Jiaye Wu, Tom Goldstein, Matthias Zwicker
Abstract
Generating a boundary representation (B-rep) conditioned on a single image requires faithful reconstruction of geometry, valid topology, and support for complex shapes. We present UniBRep, a geometry-first framework that adapts a pretrained image-to-3D model to generate a feature mesh as a unified intermediate representation. Its surface provides a geometric scaffold, while spatially aligned learned features encode face-separation cues for topology recovery. Dual decoder branches generate the geometry and face-separation features; a geometry- and feature-guided construction pipeline then fits parametric surfaces, recovers boundary curves and connectivity, and assembles an explicit B-rep using a CAD kernel. Recovering topology from mesh regions avoids predefined architectural face-count limits, allowing face count to scale with shape complexity. On the standard DeepCAD benchmark, UniBRep produces valid B-reps for 80.49\% of inputs and reduces face Chamfer distance from 0.1096 to 0.0345 relative to CADDreamer. In a matched comparison, UniBRep also outperforms the HoLa public demo across all reported metrics. Further evaluations demonstrate scalability to high-complexity shapes beyond the standard 30-face range, generalization to objects outside the CAD training distribution, and qualitative transfer to real photographs.