# Deep Portrait Image Completion and Extrapolation

arXiv: https://arxiv.org/abs/1808.07757 · HTML: https://mlsanity.com/paper/1808.07757/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2018.

## Built on by (most cited first, 12 of 12)

- [Human De-occlusion: Invisible Perception and Recovery for Humans](https://mlsanity.com/paper/2103.11597/) (2021)
- [BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning](https://mlsanity.com/paper/2112.06179/) (2021)
- [CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models](https://mlsanity.com/paper/2404.15677/) (2024)
- [Factorized and Controllable Neural Re-Rendering of Outdoor Scene for Photo Extrapolation](https://mlsanity.com/paper/2207.06899/) (2022)
- [HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping](https://mlsanity.com/paper/2212.06458/) (2022)
- [Deep Face Video Inpainting via UV Mapping](https://mlsanity.com/paper/2109.00681/) (2021)
- [KBody: Towards general, robust, and aligned monocular whole-body estimation](https://mlsanity.com/paper/2304.11542/) (2023)
- [Context-aware Padding for Semantic Segmentation](https://mlsanity.com/paper/2109.07854/) (2021)
- [CompleteMe: Reference-based Human Image Completion](https://mlsanity.com/paper/2504.20042/) (2025)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Unsupervised Domain-Specific Deblurring using Scale-Specific Attention](https://mlsanity.com/paper/2112.06175/) (2021)
- [Semantic Image Completion and Enhancement using GANs](https://mlsanity.com/paper/2307.14748/) (2023)

## Abstract (arXiv)

General image completion and extrapolation methods often fail on portrait images where parts of the human body need to be recovered - a task that requires accurate human body structure and appearance synthesis. We present a two-stage deep learning framework for tacking this problem. In the first stage, given a portrait image with an incomplete human body, we extract a complete, coherent human body structure through a human parsing network, which focuses on structure recovery inside the unknown region with the help of pose estimation. In the second stage, we use an image completion network to fill the unknown region, guided by the structure map recovered in the first stage. For realistic synthesis the completion network is trained with both perceptual loss and conditional adversarial loss. We evaluate our method on public portrait image datasets, and show that it outperforms other state-of-art general image completion methods. Our method enables new portrait image editing applications such as occlusion removal and portrait extrapolation. We further show that the proposed general learning framework can be applied to other types of images, e.g. animal images.