Dezhi Peng

11

Papers

128

Total Citations

Papers (11)

FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning

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Predicting the Original Appearance of Damaged Historical Documents

Revisiting Scene Text Recognition: A Data Perspective

ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer

UPOCR: Towards Unified Pixel-Level OCR Interface

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

Implicit Feature Alignment: Learn To Convert Text Recognizer to Text Spotter

Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution

M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark