# Unsupervised Person Image Synthesis in Arbitrary Poses

arXiv: https://arxiv.org/abs/1809.10280 · HTML: https://mlsanity.com/paper/1809.10280/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2018.

## Built on by (most cited first, 30 of 55)

- [Real-time Deep Dynamic Characters](https://mlsanity.com/paper/2105.01794/) (2021)
- [Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control](https://mlsanity.com/paper/2106.02019/) (2021)
- [Driving-Signal Aware Full-Body Avatars](https://mlsanity.com/paper/2105.10441/) (2021)
- [One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field](https://mlsanity.com/paper/2304.05097/) (2023)
- [Modeling Clothing as a Separate Layer for an Animatable Human Avatar](https://mlsanity.com/paper/2106.14879/) (2021)
- [Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2407.07532/) (2024)
- [Style and Pose Control for Image Synthesis of Humans from a Single Monocular View](https://mlsanity.com/paper/2102.11263/) (2021)
- [Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects](https://mlsanity.com/paper/2112.11347/) (2021)
- [HumanGAN: A Generative Model of Humans Images](https://mlsanity.com/paper/2103.06902/) (2021)
- [Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN](https://mlsanity.com/paper/2109.06166/) (2021)
- [Cross Attention Based Style Distribution for Controllable Person Image Synthesis](https://mlsanity.com/paper/2208.00712/) (2022)
- [Learning Semantic Person Image Generation by Region-Adaptive Normalization](https://mlsanity.com/paper/2104.06650/) (2021)
- [AI Hallucinations: A Misnomer Worth Clarifying](https://mlsanity.com/paper/2401.06796/) (2024)
- [HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars](https://mlsanity.com/paper/2112.10203/) (2021)
- [SMPLitex: A Generative Model and Dataset for 3D Human Texture Estimation from Single Image](https://mlsanity.com/paper/2309.01855/) (2023)
- [HumanLiff: Layer-wise 3D Human Generation with Diffusion Model](https://mlsanity.com/paper/2308.09712/) (2023)
- [Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis](https://mlsanity.com/paper/2109.02081/) (2021)
- [Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency](https://mlsanity.com/paper/2110.05458/) (2021)
- [The Image Local Autoregressive Transformer](https://mlsanity.com/paper/2106.02514/) (2021)
- [Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis](https://mlsanity.com/paper/2111.05916/) (2021)
- [EgoRenderer: Rendering Human Avatars from Egocentric Camera Images](https://mlsanity.com/paper/2111.12685/) (2021)
- [Flow Guided Transformable Bottleneck Networks for Motion Retargeting](https://mlsanity.com/paper/2106.07771/) (2021)
- [Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera](https://mlsanity.com/paper/2203.12780/) (2022)
- [HDHumans: A Hybrid Approach for High-fidelity Digital Humans](https://mlsanity.com/paper/2210.12003/) (2022)
- [TIPS: Text-Induced Pose Synthesis](https://mlsanity.com/paper/2207.11718/) (2022)
- [HumanDiffusion: a Coarse-to-Fine Alignment Diffusion Framework for Controllable Text-Driven Person Image Generation](https://mlsanity.com/paper/2211.06235/) (2022)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [Multi-scale Attention Guided Pose Transfer](https://mlsanity.com/paper/2202.06777/) (2022)
- [Real-Time Neural Character Rendering with Pose-Guided Multiplane Images](https://mlsanity.com/paper/2204.11820/) (2022)
- [Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis](https://mlsanity.com/paper/2210.01559/) (2022)

## Abstract (arXiv)

We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the image of the same person under the new pose, synthesizing novel views of the parts visible in the input image and hallucinating those that are not seen. This problem has recently been addressed in a supervised manner, i.e., during training the ground truth images under the new poses are given to the network. We go beyond these approaches by proposing a fully unsupervised strategy. We tackle this challenging scenario by splitting the problem into two principal subtasks. First, we consider a pose conditioned bidirectional generator that maps back the initially rendered image to the original pose, hence being directly comparable to the input image without the need to resort to any training image. Second, we devise a novel loss function that incorporates content and style terms, and aims at producing images of high perceptual quality. Extensive experiments conducted on the DeepFashion dataset demonstrate that the images rendered by our model are very close in appearance to those obtained by fully supervised approaches.