Hierarchical Neural Coding for Controllable CAD Model Generation
read the original abstract
This paper presents a novel generative model for Computer Aided Design (CAD) that 1) represents high-level design concepts of a CAD model as a three-level hierarchical tree of neural codes, from global part arrangement down to local curve geometry; and 2) controls the generation or completion of CAD models by specifying the target design using a code tree. Concretely, a novel variant of a vector quantized VAE with "masked skip connection" extracts design variations as neural codebooks at three levels. Two-stage cascaded auto-regressive transformers learn to generate code trees from incomplete CAD models and then complete CAD models following the intended design. Extensive experiments demonstrate superior performance on conventional tasks such as random generation while enabling novel interaction capabilities on conditional generation tasks. The code is available at https://github.com/samxuxiang/hnc-cad.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
-
CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
CADFit recovers complex editable CAD construction sequences from meshes via IoU-driven hybrid optimization and outperforms prior mesh-to-CAD methods on volumetric IoU, Chamfer Distance, and invalid program ratio.
-
CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization
CADFit recovers complex editable CAD construction sequences from meshes via IoU-driven hybrid optimization over structured programs, outperforming prior methods on volumetric IoU, Chamfer Distance, and invalid ratio.
-
Pointer-CAD v2: Plan-Then-Construct CAD Generation with Dimension-Aware Parametric Precision
Pointer-CAD v2 decouples planning from construction in LLM-based CAD generation by using a pointer mechanism to reference continuous parameters from a design plan, paired with new hierarchical accuracy metrics.
-
Memory-Augmented Reinforcement Learning Agent for CAD Generation
Memory-augmented RL agent with case and skill libraries plus dynamic retrieval improves success rate and geometric consistency for complex CAD model generation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.