Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection
2026-03-04 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputation and Language
AI summaryⓘ
The authors present Pointer-CAD, a new method to help computers create CAD models more accurately. Unlike previous methods that represent CAD steps as simple command sequences, their approach uses pointers to select exact parts of the model, which helps with complex edits and reduces errors. They trained their system on a large dataset with detailed descriptions to improve performance. Their experiments show that Pointer-CAD makes fewer mistakes in building 3D shapes compared to earlier methods.
CAD modelsLarge Language Modelspointer-based representationboundary representation (B-rep)command sequencemodel generationquantization errortopological errorsdata annotationnatural language descriptions
Authors
Dacheng Qi, Chenyu Wang, Jingwei Xu, Tianzhe Chu, Zibo Zhao, Wen Liu, Wenrui Ding, Yi Ma, Shenghua Gao
Abstract
Constructing computer-aided design (CAD) models is labor-intensive but essential for engineering and manufacturing. Recent advances in Large Language Models (LLMs) have inspired the LLM-based CAD generation by representing CAD as command sequences. But these methods struggle in practical scenarios because command sequence representation does not support entity selection (e.g. faces or edges), limiting its ability to support complex editing operations such as chamfer or fillet. Further, the discretization of a continuous variable during sketch and extrude operations may result in topological errors. To address these limitations, we present Pointer-CAD, a novel LLM-based CAD generation framework that leverages a pointer-based command sequence representation to explicitly incorporate the geometric information of B-rep models into sequential modeling. In particular, Pointer-CAD decomposes CAD model generation into steps, conditioning the generation of each subsequent step on both the textual description and the B-rep generated from previous steps. Whenever an operation requires the selection of a specific geometric entity, the LLM predicts a Pointer that selects the most feature-consistent candidate from the available set. Such a selection operation also reduces the quantization error in the command sequence-based representation. To support the training of Pointer-CAD, we develop a data annotation pipeline that produces expert-level natural language descriptions and apply it to build a dataset of approximately 575K CAD models. Extensive experimental results demonstrate that Pointer-CAD effectively supports the generation of complex geometric structures and reduces segmentation error to an extremely low level, achieving a significant improvement over prior command sequence methods, thereby significantly mitigating the topological inaccuracies introduced by quantization error.