← Search

Honglun Zhang

3 accepted papers

2022

BTS: A Bi-Lingual Benchmark for Text Segmentation in the Wild

CVPR 2022oral

As a prerequisite of many text-related tasks such as text erasing and text style transfer, text segmentation arouses more and more attention recently. Current researches mainly focus on only English characters and digits, while few work studies Chinese characters due to the lack of public large-scal…

Cited by 20PDFScholar
2021

Towards Real-World Blind Face Restoration With Generative Facial Prior

CVPR 2021poster

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details. However, very low-quality inputs cannot offer accurate geometric prior while high-quality references are inaccessible, limiting the applicability in re…

Cited by 588PDFcodeScholar
2021

Towards Vivid and Diverse Image Colorization With Generative Color Prior

ICCV 2021poster

Colorization has attracted increasing interest in recent years. Classic reference-based methods usually rely on external color images for plausible results. A large image database or online search engine is inevitably required for retrieving such exemplars. Recent deep-learning-based methods could a…

Cited by 119PDFcodeScholar