DAG amendment for inverse control of parametric shapes
Élie Michel, Tamy Boubekeur
Abstract
Parametric shapes model objects as programs producing a geometry based on a few semantic degrees of freedom, called hyper-parameters. These shapes are the typical output of non-destructive modeling, CAD modeling or rigging. However they suffer from the core issue of being manipulated only indirectly, through a series of values rather than the geometry itself. In this paper, we introduce an amendment process of the underlying direct acyclic graph (DAG) of a parametric shape. This amendment enables a local differentiation of the shape w.r.t. its hyper-parameters that we leverage to provide interactive direct manipulation of the output. By acting on the shape synthesis process itself, our method is agnostic to the variations of the connectivity and topology that may occur in its output while changing the input hyper-parameters. Furthermore, our method is oblivious to the internal logic of the DAG nodes. We illustrate our approach on a collection of examples combining the typical nodes found in modern parametric modeling packages - such as deformation, booleans and surfacing operators - for which our method provides the user with inverse control over the hyper-parameters through a brush stroke metaphor.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 6b5f97e8-29e3-4450-8a14-38a2380d9e21Cited by top-tier papers8
- pARam: Leveraging Parametric Design in Extended Reality to Support the Personalization of Artifacts for Personal FabricationEvgeny Stemasov, Simon Demharter, Max Rädler, Jan Gugenheimer et al.CHI 2024 · 24 citations
- ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured PrimitivesR. Kenny Jones, Paul Guerrero, Niloy J. Mitra, Daniel RitchieSIGGRAPH 2023 · 19 citations
- Understanding and Supporting Debugging Workflows in CADFelix Hähnlein, Gilbert Bernstein, Adriana SchulzUIST 2024 · 5 citations
- B-rep Matching for Collaborating Across CAD SystemsBenjamin T. Jones, James Noeckel, Milin Kodnongbua, Ilya Baran et al.SIGGRAPH 2023 · 4 citations
- CADTalk: An Algorithm and Benchmark for Semantic Commenting of CAD ProgramsHaocheng Yuan, Jing Xu, Hao Pan, Adrien Bousseau et al.CVPR 2024 · 3 citations
Builds on5
- AMASS: Archive of Motion Capture As Surface ShapesNaureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll et al.ICCV 2019 · 1,784 citations
- Inference Stage Optimization for Cross-scenario 3D Human Pose EstimationJianfeng Zhang, Xuecheng Nie, Jiashi FengNeurIPS 2020 · 53 citations
- Human-in-the-loop differential subspace search in high-dimensional latent spaceChia-Hsing Chiu, Yuki Koyama, Yu-Chi Lai, Takeo Igarashi et al.SIGGRAPH 2020 · 45 citations
- Interactive Exploration and Refinement of Facial Expression using Manifold LearningRinat Abdrashitov, Fanny Chevalier, Karan SinghUIST 2020 · 15 citations
- Learning Generative Models of Shape HandlesMatheus Gadelha, Giorgio Gori, Duygu Ceylan, Radomír Mech et al.CVPR 2020
Related papers
- Squidgets: Sketch-based Widget Design for Scene ManipulationJoonho Kim, Fanny Chevalier, Karan SinghUIST 2025
- SPAGHETTI: editing implicit shapes through part aware generationAmir Hertz, Or Perel, Raja Giryes, Olga Sorkine-Hornung et al.SIGGRAPH 2022 · 59 citations
- Neural scene graph renderingJonathan Granskog, Till N. Schnabel, Fabrice Rousselle, Jan NovákSIGGRAPH 2021 · 13 citations
- CADModelScope: Revealing the Dependency Structure Behind Parametric Computer-Aided Design ModelsYuanzhe Deng, Zhijing Zhang, Shurui Zhou, Alison OlechowskiCHI 2026 · 1 citation
- Understanding the Challenges of OpenSCAD Users for 3D PrintingJohann Felipe Gonzalez Avila, Thomas Pietrzak, Audrey Girouard, Géry CasiezCHI 2024 · 6 citations
