SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.14726 · CVPR · 2023

Learning Generative Structure Prior for Blind Text Image Super-resolution

Wangmeng Zuo, Chen Change Loy, Xiaoming Li

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

01 234152622 789 ÿ 6ÿ 9 9 ÿ 01ÿ ÿ ÿ 9 ÿ 9 ÿ ÿ ÿ ! ÿ 6ÿ 9 9 ÿ 01ÿ ÿ ÿ 9 ÿ 9 ÿ ÿ !9 Figure 1. Results obtained with TBSRN [7], TATT [41] and our approach on the segments of Chinese text image cropped from a real lowresolution invoice and a signboard. Both baselines are re-trained with elaborated degradations as in BSRGAN [75] and Real-ESRGAN [66].

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2303.14726")
get_code_for_paper("2303.14726")
have("2303.14726")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2303.14726.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2303.14726.svg)](https://syntology.ai/paper/2303.14726)

Connect an agent — have() is free.