A Video Object Removal Framework
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
Organization Card
FudanCVL
Hello, there. š We are a research group from Fudan University, led by Prof. Henghui Ding. Our research focuses on computer vision and machine learning. For more details about our work and team members, please visit here.
models 9
FudanCVL/OcclusionFormer
Text-to-Image ā¢ Updated ā¢ 1
FudanCVL/EffectErase
Video-to-Video ā¢ Updated ā¢ 341 ā¢ 7
FudanCVL/GlyphPrinter
Updated ā¢ 1
FudanCVL/SceneDesigner
Updated
FudanCVL/OISA-Train
Updated
FudanCVL/OISA-1B-OmniAVS
2B ā¢ Updated ā¢ 24
FudanCVL/MOSEv2_baseline
Updated
FudanCVL/DMA
Updated
FudanCVL/RefSplat
Updated
datasets 15
FudanCVL/SA-Z
Updated ā¢ 18
FudanCVL/AVTrack
Updated ā¢ 29
FudanCVL/NEST_250323_250411
Viewer ā¢ Updated ā¢ 1.51k ā¢ 67 ā¢ 1
FudanCVL/EffectErase
Viewer ā¢ Updated ā¢ 781k ā¢ 758 ā¢ 16
FudanCVL/GlyphCorrector
Updated ā¢ 20 ā¢ 1
FudanCVL/ObjectPose9D
Viewer ā¢ Updated ā¢ 125k ā¢ 40 ā¢ 1
FudanCVL/MeViSv2
Updated ā¢ 536 ā¢ 2
FudanCVL/gRefCOCO
Preview ā¢ Updated ā¢ 176
FudanCVL/Cut-VOS
Preview ā¢ Updated ā¢ 18 ā¢ 1
FudanCVL/OmniAVS
Viewer ā¢ Updated ā¢ 2.97M ā¢ 164 ā¢ 1