FudanCVL

university

https://github.com/FudanCVL

AI & ML interests

AIGC, Segmentation, World Model

Recent Activity

JinyuLiu updated a dataset about 11 hours ago

FudanCVL/Unison

aleeyanger new activity about 16 hours ago

FudanCVL/EffectErase:MASKs

aleeyanger new activity about 16 hours ago

FudanCVL/EffectErase:[bot] Conversion to Parquet

View all activity

Papers

SAM2Matting: Generalized Image and Video Matting

OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation

View all Papers

FudanCVL 's papers 5

Submitted by

Henghui Ding

SAM2Matting: Generalized Image and Video Matting

FudanCVL

Submitted by

Henghui Ding

OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation

FudanCVL

Submitted by

Henghui Ding

EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing

FudanCVL

Submitted by

Henghui Ding

GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering

FudanCVL

Submitted by

Henghui Ding

MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation

FudanCVL