FudanCVL/OcclusionFormer
Text-to-Image ā¢ Updated ā¢ 2
FudanCVL
university
AI & ML interests
AIGC, Segmentation, World Model
Recent Activity
View all activity
Papers
OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation
EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing