Search Results for author:
Found 4 papers, 4 papers with code
TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution
Moreover, our proposed MRD module is plug-and-play that effectively sharpens the text edges produced by SOTA methods.
DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization
Considering this phenomenon, we propose Discriminability-Driven Graph Network (DDG-Net), which explicitly models ambiguous snippets and discriminative snippets with well-designed connections, preventing the transmission of ambiguous information and enhancing the discriminability of snippet-level representations.
Weakly-supervised Temporal Action Localization
Weakly Supervised Temporal Action Localization
DocDiff: Document Enhancement via Residual Diffusion Models
Removing degradation from document images not only improves their visual quality and readability, but also enhances the performance of numerous automated document analysis and recognition tasks.
GDB: Gated convolutions-based Document Binarization
However, existing methods can not extract stroke edges finely, mainly due to the fair-treatment nature of vanilla convolutions and the extraction of stroke edges without adequate supervision by boundary-related information.
Ranked #1 on
Binarization
on H-DIBCO 2014
