all AI news
ObjBlur: A Curriculum Learning Approach With Progressive Object-Level Blurring for Improved Layout-to-Image Generation
April 12, 2024, 4:45 a.m. | Stanislav Frolov, Brian B. Moser, Sebastian Palacio, Andreas Dengel
cs.CV updates on arXiv.org arxiv.org
Abstract: We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels. Our method is based on progressive object-level blurring, which effectively stabilizes training and enhances the quality of generated images. This curriculum learning strategy systematically applies varying degrees of blurring to individual objects or the background during training, starting from strong blurring to progressively cleaner images. Our findings …
abstract arxiv cs.cv curriculum curriculum learning image image generation image generation models images labels novel object training type
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
AI Engineering Manager
@ M47 Labs | Barcelona, Catalunya [Cataluña], Spain