SIGGRAPH 2026 Conference Papers
Dafei Qin1,2
Rui Xu1,2
Zeyu Shen3
Kaichun Qiao4,2
Hongyang Lin4,2
Qixuan Zhang4,2
Huaijin Pi1
Lan Xu4
Jingyi Yu4
Wenping Wang5
Taku Komura1
1The University of Hong Kong 2Deemos Technology 3Institute of Software, Chinese Academy of Sciences 4ShanghaiTech University 5Texas A&M University
ParaCAD is an autoregressive framework for point-cloud-conditioned B-Rep generation that operates directly on native parametric surfaces. It explicitly encodes exact surface types and continuous parameters, then recovers valid B-Reps through global surface intersection and optimization.
- Release tokenizer
- Release inference code
- Release training code
Generative CAD modeling has broad design and application potential. Despite significant advances in Boundary Representation (B-Rep) generation, the dominant representation in CAD, existing methods largely depend on uniformly sampled point- or grid-based geometry representations, sacrificing native surface types and parameters and thereby limiting geometric fidelity and downstream usability. We present ParaCAD, an autoregressive framework for point-cloud-conditioned B-Rep generation that directly operates on native parametric surfaces. ParaCAD introduces a surface-centric tokenization that explicitly encodes each face by its exact surface type and continuous parameters, preserving the intrinsic semantics of CAD geometry. Our model first generates parametric surfaces with constrained UV domains, and then constructs a valid B-Rep by globally intersecting these surfaces to recover edges and vertices. ParaCAD places point-cloud-conditioned generation at the core of B-Rep synthesis, making it practical for user-guided reconstruction and seamless integration into existing 3D generation pipelines. Extensive experiments demonstrate that ParaCAD produces accurate B-Reps with faithful point-cloud alignment, outperforming point-based baselines in geometric precision, robustness, watertightness and downstream usability.