ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models
Paper
•
2506.09740
•
Published
•
1
Qin Zhou
Matrix53
AI & ML interests
Computer Vision, Diffusion Model, Video Generation
Recent Activity
authored
a paper
2 months ago
ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level
Text-Image Alignment in Diffusion Models
authored
a paper
2 months ago
Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter
upvoted
a
collection
2 months ago
Papers
Organizations
None yet
authored
2
papers
2 months ago