# Structure First Detail Next: Image Inpainting with Pyramid Generator

arXiv: https://arxiv.org/abs/2106.08905 · HTML: https://mlsanity.com/paper/2106.08905/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 25 of 25)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Pluralistic Image Completion](https://mlsanity.com/paper/1903.04227/) (2019)
- [High-Fidelity Pluralistic Image Completion with Transformers](https://mlsanity.com/paper/2103.14031/) (2021)
- [Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting](https://mlsanity.com/paper/2005.09704/) (2020)
- [StructureFlow: Image Inpainting via Structure-aware Appearance Flow](https://mlsanity.com/paper/1908.03852/) (2019)
- [Recurrent Feature Reasoning for Image Inpainting](https://mlsanity.com/paper/2008.03737/) (2020)
- [Coherent Semantic Attention for Image Inpainting](https://mlsanity.com/paper/1905.12384/) (2019)
- [Learning Pyramid-Context Encoder Network for High-Quality Image Inpainting](https://mlsanity.com/paper/1904.07475/) (2019)
- [High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis](https://mlsanity.com/paper/1611.09969/) (2016)
- [Shift-Net: Image Inpainting via Deep Feature Rearrangement](https://mlsanity.com/paper/1801.09392/) (2018)
- [Generative Face Completion](https://mlsanity.com/paper/1704.05838/) (2017)
- [High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling](https://mlsanity.com/paper/2005.11742/) (2020)
- [Region Normalization for Image Inpainting](https://mlsanity.com/paper/1911.10375/) (2019)
- [Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes](https://mlsanity.com/paper/2003.06877/) (2020)
- [Zoom-to-Inpaint: Image Inpainting with High-Frequency Details](https://mlsanity.com/paper/2012.09401/) (2020)

## Built on by (most cited first, 1 of 1)

- [Internal Diverse Image Completion](https://mlsanity.com/paper/2212.10280/) (2022)

## Abstract (arXiv)

Recent deep generative models have achieved promising performance in image inpainting. However, it is still very challenging for a neural network to generate realistic image details and textures, due to its inherent spectral bias. By our understanding of how artists work, we suggest to adopt a `structure first detail next' workflow for image inpainting. To this end, we propose to build a Pyramid Generator by stacking several sub-generators, where lower-layer sub-generators focus on restoring image structures while the higher-layer sub-generators emphasize image details. Given an input image, it will be gradually restored by going through the entire pyramid in a bottom-up fashion. Particularly, our approach has a learning scheme of progressively increasing hole size, which allows it to restore large-hole images. In addition, our method could fully exploit the benefits of learning with high-resolution images, and hence is suitable for high-resolution image inpainting. Extensive experimental results on benchmark datasets have validated the effectiveness of our approach compared with state-of-the-art methods.