A Video Object Removal Framework
FudanCVL
university
AI & ML interests
AIGC, Segmentation, World Model
Recent Activity
Papers
GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation
Motion-Guided Few-Shot Video Object Segmentation
Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation
A Video Object Removal Framework
Models and datasets for GlyphPrinter
MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation
Motion-Guided Few-Shot Video Object Segmentation
MOSE: Complex Video Object Segmentation Dataset
Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation