JiahuiYu/generative_inpainting
TensorFlow implementation of DeepFill v1/v2 generative image inpainting models using contextual attention and gated convolutions.
Not currently ranked — collecting fresh signals.
star history
This repository provides an open-source framework for free-form image inpainting, implementing two published deep learning methods: DeepFill v1 with contextual attention (CVPR 2018) and DeepFill v2 with gated convolution (ICCV 2019 Oral). The system uses generative adversarial networks to fill missing regions in images with realistic content. It is built on TensorFlow and includes pretrained models along with training code.
Frequently asked
- What is JiahuiYu/generative_inpainting?
- TensorFlow implementation of DeepFill v1/v2 generative image inpainting models using contextual attention and gated convolutions.
- Is generative_inpainting open source?
- Yes — JiahuiYu/generative_inpainting is an open-source project tracked on heatdrop.
- What language is generative_inpainting written in?
- JiahuiYu/generative_inpainting is primarily written in Python.
- How popular is generative_inpainting?
- JiahuiYu/generative_inpainting has 3.5k stars on GitHub.
- Where can I find generative_inpainting?
- JiahuiYu/generative_inpainting is on GitHub at https://github.com/JiahuiYu/generative_inpainting.