Should I render or should AI Generate? Crafting Synthetic Semantic Segmentation Datasets with Controlled Generation

This work explores the integration of generative AI models for automatically generating synthetic image-labeled data. Our approach leverages controllable Diffusion Models to generate synthetic variations of semantically labeled images. Synthetic datasets for semantic segmentation struggle to represe...

Description complète

Détails bibliographiques

Publié dans:	IEEE computer graphics and applications. - 1991. - PP(2025) vom: 21. März
Auteur principal:	Mures, Omar A (Auteur)
Autres auteurs:	Silva, Manuel, Lijo-Sanchez, Manuel, Padron, Emilio J, Iglesias-Guitian, Jose A
Format:	Article en ligne
Langue:	English
Publié:	2025
Accès à la collection:	IEEE computer graphics and applications
Sujets:	Journal Article