SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation

Sathvik Reddy Chereddy, John Femiani
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:10199-10215, 2025.

Abstract

We present SketchDNN, a generative model for synthesizing CAD sketches that jointly models both continuous parameters and discrete class labels through a unified continuous-discrete diffusion process. Our core innovation is Gaussian-Softmax diffusion, where logits perturbed with Gaussian noise are projected onto the probability simplex via a softmax transformation, facilitating blended class labels for discrete variables. This formulation addresses 2 key challenges, namely, the heterogeneity of primitive parameterizations and the permutation invariance of primitives in CAD sketches. Our approach significantly improves generation quality, reducing Fréchet Inception Distance (FID) from 16.04 to 7.80 and negative log-likelihood (NLL) from 84.8 to 81.33, establishing a new state-of-the-art in CAD sketch generation on the SketchGraphs dataset.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-chereddy25a, title = {{S}ketch{DNN}: Joint Continuous-Discrete Diffusion for {CAD} Sketch Generation}, author = {Chereddy, Sathvik Reddy and Femiani, John}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {10199--10215}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/chereddy25a/chereddy25a.pdf}, url = {https://proceedings.mlr.press/v267/chereddy25a.html}, abstract = {We present SketchDNN, a generative model for synthesizing CAD sketches that jointly models both continuous parameters and discrete class labels through a unified continuous-discrete diffusion process. Our core innovation is Gaussian-Softmax diffusion, where logits perturbed with Gaussian noise are projected onto the probability simplex via a softmax transformation, facilitating blended class labels for discrete variables. This formulation addresses 2 key challenges, namely, the heterogeneity of primitive parameterizations and the permutation invariance of primitives in CAD sketches. Our approach significantly improves generation quality, reducing Fréchet Inception Distance (FID) from 16.04 to 7.80 and negative log-likelihood (NLL) from 84.8 to 81.33, establishing a new state-of-the-art in CAD sketch generation on the SketchGraphs dataset.} }
Endnote
%0 Conference Paper %T SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation %A Sathvik Reddy Chereddy %A John Femiani %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-chereddy25a %I PMLR %P 10199--10215 %U https://proceedings.mlr.press/v267/chereddy25a.html %V 267 %X We present SketchDNN, a generative model for synthesizing CAD sketches that jointly models both continuous parameters and discrete class labels through a unified continuous-discrete diffusion process. Our core innovation is Gaussian-Softmax diffusion, where logits perturbed with Gaussian noise are projected onto the probability simplex via a softmax transformation, facilitating blended class labels for discrete variables. This formulation addresses 2 key challenges, namely, the heterogeneity of primitive parameterizations and the permutation invariance of primitives in CAD sketches. Our approach significantly improves generation quality, reducing Fréchet Inception Distance (FID) from 16.04 to 7.80 and negative log-likelihood (NLL) from 84.8 to 81.33, establishing a new state-of-the-art in CAD sketch generation on the SketchGraphs dataset.
APA
Chereddy, S.R. & Femiani, J.. (2025). SketchDNN: Joint Continuous-Discrete Diffusion for CAD Sketch Generation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:10199-10215 Available from https://proceedings.mlr.press/v267/chereddy25a.html.

Related Material