Wenjie Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wenjie Guo has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Shibin Wang
School of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, China
1 shared publication - Xuening Guo
Information Management Department, Henan Normal University, Xinxiang 453007, China
1 shared publication
Latest Publications
- Open Access
- 29 May 2025
- Published by MDPI AG in Electronics
- Vol. 14 (11) , 2218
MD-GAN: Multi-Scale Diversity GAN for Large Masks Inpainting
Image inpainting approaches have made considerable progress with the assistance of generative adversarial networks (GANs) recently. However, current inpainting methods are incompetent in handling the cases with large masks and they generally suffer from unreasonable structure. We find that the main reason is the lack of an effective receptive field in the inpainting network. To alleviate this issue, we propose a new two-stage inpainting model called MD-GAN, which is a multi-scale diverse GAN. We inject dense combinations of dilated convolutions in multiple scales of inpainting networks to obtain more effective receptive fields. In fact, the result of inpainting large masks is generally not uniquely deterministic. To this end, we newly propose the multi-scale probabilistic diverse module, which achieves diverse content generation by spatial-adaptive normalization. Meanwhile, the convolutional block attention module is introduced to improve the ability to extract complex features. Perceptual diversity loss is added to enhance diversity. Extensive experiments on benchmark datasets including CelebA-HQ, Places2 and Paris Street View demonstrate that our approach is able to effectively inpaint diverse and structurally reasonable images.
- 29 May 2025
- Published by MDPI AG in Electronics
- Vol. 14 (11) , 2218
Open AccessMD-GAN: Multi-Scale Diversity GAN for Large Masks Inpainting
Image inpainting approaches have made considerable progress with the assistance of generative adversarial networks (GANs) recently. However, current inpainting methods are incompetent in handling the cases with large masks and they generally suffer from unreasonable structure. We find that the main reason is the lack of an effective receptive field in the inpainting network. To alleviate this issue, we propose a new two-stage inpainting model called MD-GAN, which is a multi-scale diverse GAN. We inject dense combinations of dilated convolutions in multiple scales of inpainting networks to obtain more effective receptive fields. In fact, the result of inpainting large masks is generally not uniquely deterministic. To this end, we newly propose the multi-scale probabilistic diverse module, which achieves diverse content generation by spatial-adaptive normalization. Meanwhile, the convolutional block attention module is introduced to improve the ability to extract complex features. Perceptual diversity loss is added to enhance diversity. Extensive experiments on benchmark datasets including CelebA-HQ, Places2 and Paris Street View demonstrate that our approach is able to effectively inpaint diverse and structurally reasonable images.