Composable CAD: Sketch-to-CAD Program Synthesis in Parts
Yuanbo Li, Vivian Liu, Sean Liu, Justin Matejka
Abstract
Designers often build CAD models part by part, and may iterate on individual components throughout the design process. Recent vision-language models (VLMs) can synthesize CAD programs from sketches, but generating parts independently does not ensure that they are composable: components may lose the intended proportions and alignments or fail to join correctly where they meet. We present Composable CAD, a framework that uses off-the-shelf VLMs to synthesize a design space of independently sampled, interchangeable component programs, where any selection composes into a coherent CAD model. We recover design constraints from the sketch and use them to construct a coarse proxy that establishes how the components are sized, aligned, and attached. We then generate each component independently from its proxy and apply a deterministic rewrite to ensure that neighboring components meet at their prescribed interfaces. We evaluate Composable CAD across a range of objects and sketch styles and conduct two user studies. Compared to VLM-only baselines, our method produces more detailed, composable designs.
Create a lesson
Related papers
Toolpath Overhang Optimization for the Large-Format 3D Printing of Bespoke Shapes
Yefan Zhi, Masoud Akbarzadeh
Piecewise CMC Segmentation for Fluidic Shaping
Abhinit Sati, Jacob Garrett, Valeri Frumkin et al.
SemEllipsoid: Semantic-aware Shape Abstraction with Ellipsoid
Kuankuan Cheng, Haocheng Yuan, Changjian Li
Dynamic Skinning: Kinematics-Driven Cartoon Effects for Articulated Characters
Damien Rohmer, Karim Salem, Niranjan Kalyanasundaram et al.
TalkFlow: Structured Latent Flow Matching for Speech Driven Holistic Motion Generation
Xinmu Wang, Fumi Honda, Xiang Gao et al.
Greenscapes: Optimized Vegetation Configurations in Cities
Patryk Bartkowiak, Marcin Marlewski, Paweł Wójcik et al.