Improving Cross-modal Alignment for Text-Guided Image Inpainting

Yucheng Zhou, Guodong Long


Abstract
Text-guided image inpainting (TGII) aims to restore missing regions based on a given text in a damaged image. Existing methods are based on a strong vision encoder and a cross-modal fusion model to integrate cross-modal features. However, these methods allocate most of the computation to visual encoding, while light computation on modeling modality interactions. Moreover, they take cross-modal fusion for depth features, which ignores a fine-grained alignment between text and image. Recently, vision-language pre-trained models (VLPM), encapsulating rich cross-modal alignment knowledge, have advanced in most multimodal tasks. In this work, we propose a novel model for TGII by improving cross-modal alignment (CMA). CMA model consists of a VLPM as a vision-language encoder, an image generator and global-local discriminators. To explore cross-modal alignment knowledge for image restoration, we introduce cross-modal alignment distillation and in-sample distribution distillation. In addition, we employ adversarial training to enhance the model to fill the missing region in complicated structures effectively. Experiments are conducted on two popular vision-language datasets. Results show that our model achieves state-of-the-art performance compared with other strong competitors.
Anthology ID:
2023.eacl-main.250
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3445–3456
Language:
URL:
https://aclanthology.org/2023.eacl-main.250
DOI:
10.18653/v1/2023.eacl-main.250
Bibkey:
Cite (ACL):
Yucheng Zhou and Guodong Long. 2023. Improving Cross-modal Alignment for Text-Guided Image Inpainting. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3445–3456, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Improving Cross-modal Alignment for Text-Guided Image Inpainting (Zhou & Long, EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.250.pdf
Video:
 https://aclanthology.org/2023.eacl-main.250.mp4