Patch-Based Image Inpainting with Generative Adversarial Networks
By Ugur Demir, Gözde B. Ünal. arXiv.org, 2018
314 citations recorded by the source corpus.
Area of image inpainting over relatively large missing regions recently advanced substantially through adaptation of dedicated deep neural networks. However, current network solutions still introduce undesired artifacts and noise to the repaired regions. We present an image inpainting method that is based on the celebrated generative adversarial network (GAN) framework. The proposed PGGAN method includes a discriminator network that combines a global GAN (G-GAN) architecture with a patchGAN approach. PGGAN first shares network layers between G-GAN and patchGAN, then splits paths to produce two adversarial losses that feed the generator network in order to capture both local continuity of image texture and pervasive global features in images. The proposed framework is evaluated extensively, and the results including comparison to recent state-of-the-art demonstrate that it achieves considerable improvements on both visual and quantitative evaluations.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/28ea4b757ff13bb9c42d4510e039404fbb256472
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Peihao Zhu
- Peter Wonka
- Rameen Abdal
- Niloy J. Mitra
- Daniel Cohen-Or
- Yipeng Qin
- Ming-Hsuan Yang
- Eli Shechtman
Citations in the corpus
- A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, methodology): “The PG-GAN [46] proposed an idea by combining the global GAN [47] with a patchwise GAN approach [48] to design a new discriminator network.”
- Image2StyleGAN++: How to Edit the Embedded Images? (2019, methodology): “Such embedding algorithms can be used to analyze the limitations of GANs [5], do image inpainting [8, 39, 38, 36], local image editing [40, 17], global image transformations such as image morphing and expression transfer [1], and few-shot video generation [35, 34].”
- Labels4Free: Unsupervised Segmentation using StyleGAN (2021, background): “Examples include various image and video editing tasks, image inpainting [13, 47, 46, 41], local image editing [42, 2], low bit-rate video conferencing [40], image super resolution [28, 12], image colorization [4, 27], and extracting 3D models [30].”
- SEAN: Image Synthesis With Semantic Region-Adaptive Normalization (2019, unknown): “image inpainting [48, 11], image manipulation [52, 5, 1] and texture synthesis [29, 43, 12].”