Royalvice / DocDiff
ACM Multimedia 2023: DocDiff: Document Enhancement via Residual Diffusion Models. Also contains 1597 red seals in Chinese scenes, along with their corresponding binary masks.
☆222Updated 3 weeks ago
Related projects: ⓘ
- This repository contains a paper collection of the methods for document image processing, including appearance enhancement, deshadow, dew…☆149Updated last week
- The official code of CornerTransformer (ECCV 2022, Oral) on top of MMOCR.☆136Updated last year
- ☆146Updated 6 months ago
- A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution (CVPR2022)☆168Updated 2 years ago
- This repository is the implementation of "Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Contex…☆77Updated last year
- DocTr++ in PaddlePaddle☆37Updated last month
- [ICCV 2023] Code base for Revisiting Scene Text Recognition: A Data Perspective☆165Updated 10 months ago
- This repository contains datasets and baselines for benchmarking Chinese text recognition.☆424Updated last year
- Official code for DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degra…