Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vice, Jordan, Akhtar, Naveed, Shah, Mubarak, Hartley, Richard, Mian, Ajmal
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2411.13982