Abstract
With the development of image restoration technology based on deep learning, more complex problems are being solved, especially in image semantic inpainting based on context. Nowadays, image semantic inpainting techniques are becoming more mature. However, due to the limitations of memory, the instability of training, and the lack of sample diversity, the results of image restoration are still encountering difficult problems, such as repairing the content of glitches which cannot be well integrated with the original image. Therefore, we propose an image inpainting network based on Wasserstein generative adversarial network (WGAN) distance. With the corresponding technology having been adjusted and improved, we attempted to use the Adam algorithm to replace the traditional stochastic gradient descent, and another algorithm to optimize the training used in recent years. We evaluated our algorithm on the ImageNet dataset. We obtained high-quality restoration results, indicating that our algorithm improves the clarity and consistency of the image.
Highlights
Image inpainting has been an important topic in the area of computer vision for many years
With the development of image restoration technology based on deep learning, more complex problems are being solved, especially in image semantic inpainting based on context
We propose an image inpainting network based on Wasserstein generative adversarial network (WGAN) distance
Summary
Image inpainting has been an important topic in the area of computer vision for many years. Deep learning is used to accomplish image inpainting tasks through some trained image models that can be used to repair images for specific damage situations. If a well-trained deep learning network can better repair the image of 32 × 32 missing area, but it may not show good results in image with 10 × 10 missing area. The main contributions of this paper can be summarized in three aspects: Compared with the current popular DCGAN-based image inpainting method, we use WGAN [4] technology. In this way, no matter what the shape and location of the lost area, we can perform image restoration based on the image context semantics. Our model can generate repair results that are beautiful and visually more similar to the original image
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
