5 papers
SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion
Wenbin Duan, Yan Shu, Zhuoyuan Fu +4
Rectified-flow-based diffusion transformers, particularly FLUX, have demonstrated outstanding performance in high-quality image generation. However, achieving fast and accurate inv…
StyleTextGen: Style-Conditioned Multilingual Scene Text Generation
Zeyu Chen, Fangmin Zhao, Yan Shu +3
Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across cha…
TADoc: Robust Time-Aware Document Image Dewarping
Fangmin Zhao, Weichao Zeng, Zhenhang Li +2
Flattening curved, wrinkled, and rotated document images captured by portable photographing devices, termed document image dewarping, has become an increasingly important task with…
Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion
Fangmin Zhao, Weichao Zeng, Zhenhang Li +4
Removing various degradations from damaged documents greatly benefits digitization, downstream document analysis, and readability. Previous methods often treat each restoration tas…
Visual Text Processing: A Comprehensive Review and Unified Evaluation
Yan Shu, Weichao Zeng, Fangmin Zhao +9
Visual text is a crucial component in both document and scene images, conveying rich semantic information and attracting significant attention in the computer vision community. Bey…