Guided Image Inpainting: Replacing an Image Region by Pulling Content From Another Image

By Yinan Zhao, Brian L. Price, Scott D. Cohen, Danna Gurari. 2018

43 citations recorded by the source corpus.

Deep generative models have shown success in automatically synthesizing missing image regions using surrounding context. However, users cannot directly decide what content to synthesize with such approaches.We propose an end-to-end network for image inpainting that uses a different image to guide the synthesis of new content to fill the hole. A key challenge addressed by our approach is synthesizing new content in regions where the guidance image and the context of the original image are inconsistent. We conduct four studies that demonstrate our method yields more realistic image inpainting results over seven baselines.

Subfields: Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Graphics and Computer-Aided Design

1. Youngjoo Jo
2. Jongyoul Park

In Computer Vision and Pattern Recognition

1. Baotian Hu
2. Youngjoo Jo
3. Qingcai Chen
4. Lisai Zhang
5. Noor Almaadeed
6. Jongyoul Park
7. Somaya Ali Al-Máadeed
8. Omar ElHarrouss

In Generative Models

1. Youngjoo Jo
2. Qingcai Chen
3. Lisai Zhang
4. Jongyoul Park
5. Baotian Hu
6. Shuoran Jiang

Citations in the corpus

• SC-FEGAN: Face Editing Generative Adversarial Network With User’s Sketch and Color (2019, methodology): “Several works that have improved upon these limitations include DeepFillv2 [17], which utilizes user sketches as inputs, a work that utilized user’s sketch as an input, and GuidedInpainting [21], in which part of another image is used as an input to restore the missing parts.”
• Coherent Semantic Attention for Image Inpainting (2019, unknown): “Learning approaches [38, 22, 31, 37, 41, 7, 42] often use deep learning and GAN strategy to generate pixels of the hole.”
• Text-Guided Neural Image Inpainting (2020, methodology): “Some methods are also based on patch match algorithms, but use external image sources [5, 43] such as search engine [34].”
• Image Inpainting: A Review (2019, methodology): “For the same purpose of image inpainting, but for replacing a region of an image by another region from another image, the authors in [64] based on VGG model trained their own model.”