Document is current
Any future updates will be listed below
-
Authors
Azimi, Rambod
Grinberg, Yuri
Xu, Dan-Xia
Liboiron-Ladouceur, Odile
-
Funding
Funding for this research was provided by:
National Research Council Research Associateship Programs (AI4D-144)
- License Information
-
More Information
Article History
Received: 31 July 2025
Revised: 31 December 2025
Accepted: 29 January 2026
First Online: 9 March 2026
Declarations
:
: The authors declare that they have no conflict of interest.
: The methodology described in this paper can be replicated by readers using publicly available tools. Our Gen-Fab model builds upon the standard Pix2Pix architecture, with a key modification of injecting a stochastic latent vector at the generator bottleneck described in text in detail. All architectural details, loss functions, and training protocols are described in detail throughout the paper. We also provide full descriptions of our experimental setup, evaluation metrics (IoU, KL divergence, and Wasserstein distance), and hyperparameter choices.
