Chongyu Liu

5

Papers

54

Total Citations

Papers (5)

DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining

Predicting the Original Appearance of Damaged Historical Documents

Towards Modern Image Manipulation Localization: A Large-Scale Dataset and Novel Methods

UPOCR: Towards Unified Pixel-Level OCR Interface