FudanCVL/EffectErase
Video-to-Video ā¢ Updated ā¢ 416 ā¢ 7
FudanCVL
university
AI & ML interests
AIGC, Segmentation, World Model
Recent Activity
Papers
EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering