CVPR 2023で発表された、ドキュメント/レイアウト周りの論文
- Unifying Vision, Text, and Layout for Universal Document Processing
- GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction
- M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis
- Unifying Layout Generation With a Decoupled Diffusion Model
- LayoutDM: Transformer-Based Diffusion Model for Layout Generation
- LayoutDM: Discrete Diffusion Model for Controllable Layout Generation
- LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction
- PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout
- Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation
- Document Image Shadow Removal Guided by Color-Aware Background
- Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution
- Towards Flexible Multi-Modal Document Models
を、第59回 コンピュータビジョン勉強会@関東
https://kantocv.connpass.com/event/288902/
で広く浅く読みました。
ドキュメント文書の理解とか生成とかに興味のある方のお役に立てれば幸いです。