# Image Inpainting with External-internal Learning and Monochromic Bottleneck

arXiv: https://arxiv.org/abs/2104.09068 · HTML: https://mlsanity.com/paper/2104.09068/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 19 Apr 2021.

## Builds on (most cited first, 21 of 21)

- [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)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [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)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting](https://mlsanity.com/paper/2005.09704/) (2020)
- [Real-Time User-Guided Image Colorization with Learned Deep Priors](https://mlsanity.com/paper/1705.02999/) (2017)
- [StructureFlow: Image Inpainting via Structure-aware Appearance Flow](https://mlsanity.com/paper/1908.03852/) (2019)
- [Foreground-aware Image Inpainting](https://mlsanity.com/paper/1901.05945/) (2019)
- [Image Inpainting via Generative Multi-column Convolutional Neural Networks](https://mlsanity.com/paper/1810.08771/) (2018)
- [High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling](https://mlsanity.com/paper/2005.11742/) (2020)
- [Non-Stationary Texture Synthesis by Adversarial Expansion](https://mlsanity.com/paper/1805.04487/) (2018)
- [SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting](https://mlsanity.com/paper/1805.03356/) (2018)
- [Progressive Color Transfer with Dense Semantic Correspondences](https://mlsanity.com/paper/1710.00756/) (2017)

## Built on by (most cited first, 21 of 21)

- [HNeRV: A Hybrid Neural Representation for Videos](https://mlsanity.com/paper/2304.02633/) (2023)
- [High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization](https://mlsanity.com/paper/2211.15662/) (2022)
- [Deep Learning-based Image and Video Inpainting: A Survey](https://mlsanity.com/paper/2401.03395/) (2024)
- [Dual-Camera Super-Resolution with Aligned Attention Modules](https://mlsanity.com/paper/2109.01349/) (2021)
- [MagicQuill: An Intelligent Interactive Image Editing System](https://mlsanity.com/paper/2411.09703/) (2024)
- [Partially Does It: Towards Scene-Level FG-SBIR with Partial Input](https://mlsanity.com/paper/2203.14804/) (2022)
- [Internal Video Inpainting by Implicit Long-range Propagation](https://mlsanity.com/paper/2108.01912/) (2021)
- [Learning to Immunize Images for Tamper Localization and Self-Recovery](https://mlsanity.com/paper/2210.15902/) (2022)
- [PMAA: A Progressive Multi-scale Attention Autoencoder Model for High-performance Cloud Removal from Multi-temporal Satellite Imagery](https://mlsanity.com/paper/2303.16565/) (2023)
- [Delving Globally into Texture and Structure for Image Inpainting](https://mlsanity.com/paper/2209.08217/) (2022)
- [Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning](https://mlsanity.com/paper/2506.07227/) (2025)
- [Staging E-Commerce Products for Online Advertising using Retrieval Assisted Image Generation](https://mlsanity.com/paper/2307.15326/) (2023)
- [Interactive Image Manipulation with Complex Text Instructions](https://mlsanity.com/paper/2211.15352/) (2022)
- [Fully Context-Aware Image Inpainting with a Learned Semantic Pyramid](https://mlsanity.com/paper/2112.04107/) (2021)
- [Learning Continuous Implicit Representation for Near-Periodic Patterns](https://mlsanity.com/paper/2208.12278/) (2022)
- [SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting](https://mlsanity.com/paper/2307.14489/) (2023)
- [Multi-feature Co-learning for Image Inpainting](https://mlsanity.com/paper/2205.10578/) (2022)
- [EAA-Net: Rethinking the Autoencoder Architecture with Intra-class Features for Medical Image Segmentation](https://mlsanity.com/paper/2208.09197/) (2022)
- [E2F-Net: Eyes-to-Face Inpainting via StyleGAN Latent Space](https://mlsanity.com/paper/2403.12197/) (2024)
- [Rethinking Referring Object Removal](https://mlsanity.com/paper/2403.09128/) (2024)
- [Clutter Detection and Removal by Multi-Objective Analysis for Photographic Guidance](https://mlsanity.com/paper/2507.14553/) (2025)

## Abstract (arXiv)

Although recent inpainting approaches have demonstrated significant improvements with deep neural networks, they still suffer from artifacts such as blunt structures and abrupt colors when filling in the missing regions. To address these issues, we propose an external-internal inpainting scheme with a monochromic bottleneck that helps image inpainting models remove these artifacts. In the external learning stage, we reconstruct missing structures and details in the monochromic space to reduce the learning dimension. In the internal learning stage, we propose a novel internal color propagation method with progressive learning strategies for consistent color restoration. Extensive experiments demonstrate that our proposed scheme helps image inpainting models produce more structure-preserved and visually compelling results.