-
[pdf]
[supp]
[code]
[bibtex]@InProceedings{Hou_2022_ACCV, author = {Hou, Yujie and Chen, Jiwei Ji and Wang, Zengfu}, title = {Multi-Branch Network with Ensemble Learning for Text Removal in the Wild}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2022}, pages = {1333-1349} }
Multi-Branch Network with Ensemble Learning for Text Removal in the Wild
Abstract
The scene text removal (STR) is to substitute visually realistic backgrounds for text regions. Due to the diversity of scene text
and the intricacy of backgrounds, earlier STR approaches may not be
able to successfully remove scene texts. We discover that different networks produce different text removal results. Thus, we present a novel
STR approach with a multi-branch network to entirely erase the text
while maintaining the integrity of the backgrounds. The main branch
preserves high-resolution texture information, while two sub-branches
learn multi-scale semantic features. The complementary erasure networks
are integrated with two ensemble learning fusion mechanisms: a featurelevel fusion and an image-level fusion. Additionally, we propose a patch
attention module to perceive text location and generate text attention
features. Our method outperforms state-of-the-art approaches on both
real-world and synthetic datasets, improving PSNR by 1.78 dB in the
SCUT-EnsText dataset and 4.45 dB in the SCUT-Syn dataset.
Related Material