Differentiable 3D CAD Programs for Bidirectional Editing
Not on the map. Why?
Abstract (arXiv)
Modern CAD tools represent 3D designs not only as geometry, but also as a program composed of geometric operations, each of which depends on a set of parameters. Program representations enable meaningful and controlled shape variations via parameter changes. However, achieving desired modifications solely through parameter editing is challenging when CAD models have not been explicitly authored to expose select degrees of freedom in advance. We introduce a novel bidirectional editing system for 3D CAD programs. In addition to editing the CAD program, users can directly manipulate 3D geometry and our system infers parameter updates to keep both representations in sync. We formulate inverse edits as a set of constrained optimization objectives, returning plausible updates to program parameters that both match user intent and maintain program validity. Our approach implements an automatically differentiable domain-specific language for CAD programs, providing derivatives for this optimization to be performed quickly on any expressed program. Our system enables rapid, interactive exploration of a constrained 3D design space by allowing users to manipulate the program and geometry interchangeably during design iteration. While our approach is not designed to optimize across changes in geometric topology, we show it is expressive and performant enough for users to produce a diverse set of design variants, even when the CAD program contains a large number of parameters.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Oct 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 3; 2023: 4; 2024: 3; 2025: 1; 2026: 2.
13 papers.
Sort:
- 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
- 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
- 2022ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generationcited by 17
- 2023CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programscited by 15
- 2022Differentiable Hybrid Traffic Simulationcited by 8
- 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimizationcited by 8
- 2023Differentiable Visual Computing for Inverse Problems and Machine Learningcited by 7
- 2022Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Programcited by 6
- 2024DiffCSG: Differentiable CSG via Rasterizationcited by 6
- 2024ParSEL: Parameterized Shape Editing with Languagecited by 5
- 2025GLUE: Coordinating Pre-Trained Generative Models for System-Level Designcited by 0
- 2026MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Explorationcited by 0
- 2026CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation18 Jul 2026
- 2026MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration25 Apr 2026
- 2025GLUE: Coordinating Pre-Trained Generative Models for System-Level Design22 Dec 2025
- 2024DiffCSG: Differentiable CSG via Rasterization2 Sep 2024
- 2024ParSEL: Parameterized Shape Editing with Language30 May 2024
- 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization4 Feb 2024
- 2023CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs28 Nov 2023
- 2023Differentiable Visual Computing for Inverse Problems and Machine Learning21 Nov 2023
- 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations19 Mar 2023
- 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts27 Jan 2023
- 2022Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program25 Dec 2022
- 2022Differentiable Hybrid Traffic Simulation14 Oct 2022
1 more
- 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operationscited by 46
- 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropoutscited by 39
- 2022ComplexGen: CAD Reconstruction by B-Rep Chain Complex Generationcited by 17
- 2023CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programscited by 15
- 2022Differentiable Hybrid Traffic Simulationcited by 8
- 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimizationcited by 8
- 2023Differentiable Visual Computing for Inverse Problems and Machine Learningcited by 7
- 2022Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Programcited by 6
- 2024DiffCSG: Differentiable CSG via Rasterizationcited by 6
- 2024ParSEL: Parameterized Shape Editing with Languagecited by 5
- 2025GLUE: Coordinating Pre-Trained Generative Models for System-Level Designcited by 0
- 2026MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Explorationcited by 0
12 most cited of 13 All 13 (JSON)
- 2026CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation18 Jul 2026
- 2026MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration25 Apr 2026
- 2025GLUE: Coordinating Pre-Trained Generative Models for System-Level Design22 Dec 2025
- 2024DiffCSG: Differentiable CSG via Rasterization2 Sep 2024
- 2024ParSEL: Parameterized Shape Editing with Language30 May 2024
- 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization4 Feb 2024
- 2023CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD Programs28 Nov 2023
- 2023Differentiable Visual Computing for Inverse Problems and Machine Learning21 Nov 2023
- 2023SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations19 Mar 2023
- 2023D2CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts27 Jan 2023
- 2022Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program25 Dec 2022
- 2022Differentiable Hybrid Traffic Simulation14 Oct 2022
12 newest of 13 All 13 (JSON)