logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Memory-efficient filter-guided diffusion with domain transform filtering

delete2025-09-08
delete0
PRE
AI
G
Gustavo Lopes Tamiosso
C
Caetano Müller
L
Lucas Spagnolo Bombana
M
Manuel M. Oliveira *
DOI：10.1016/j.cag.2025.104389delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A memory-efficient approach for structure-conditioned diffusion models. • A normalization strategy that improves structural consistency and prompt alignment. • A strategy for handling image sizes FGD cannot within the same GPU memory budget. • A faster inference scheme than FGD with gains scaling with image resolution. • A memory-saving strategy that trades space for inference time.

Journal

C
computers & graphics
IF:
0
Papers:
119
Citations:
0

Organization

No organization information available