# Disentangled Person Image Generation

arXiv: https://arxiv.org/abs/1712.02621 · HTML: https://mlsanity.com/paper/1712.02621/

## Key facts

- Cited by 98 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2017.

## Built on by (most cited first, 30 of 98)

- [NeuMan: Neural Human Radiance Field from a Single Video](https://mlsanity.com/paper/2203.12575/) (2022)
- [Neural Articulated Radiance Field](https://mlsanity.com/paper/2104.03110/) (2021)
- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [Real-time Deep Dynamic Characters](https://mlsanity.com/paper/2105.01794/) (2021)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control](https://mlsanity.com/paper/2106.02019/) (2021)
- [OOD-GNN: Out-of-Distribution Generalized Graph Neural Network](https://mlsanity.com/paper/2112.03806/) (2021)
- [Neural Re-Rendering of Humans from a Single Image](https://mlsanity.com/paper/2101.04104/) (2021)
- [Neural Texture Extraction and Distribution for Controllable Person Image Synthesis](https://mlsanity.com/paper/2204.06160/) (2022)
- [Style and Pose Control for Image Synthesis of Humans from a Single Monocular View](https://mlsanity.com/paper/2102.11263/) (2021)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)
- [Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis](https://mlsanity.com/paper/2402.18078/) (2024)
- [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)
- [Single-Image 3D Human Digitization with Shape-Guided Diffusion](https://mlsanity.com/paper/2311.09221/) (2023)
- [LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?](https://mlsanity.com/paper/2310.17110/) (2023)
- [Understanding Object Dynamics for Interactive Image-to-Video Synthesis](https://mlsanity.com/paper/2106.11303/) (2021)
- [DisPose: Disentangling Pose Guidance for Controllable Human Image Animation](https://mlsanity.com/paper/2412.09349/) (2024)
- [Structure-Aware Motion Transfer with Deformable Anchor Model](https://mlsanity.com/paper/2204.05018/) (2022)
- [HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars](https://mlsanity.com/paper/2112.10203/) (2021)
- [3D-Aware Semantic-Guided Generative Model for Human Synthesis](https://mlsanity.com/paper/2112.01422/) (2021)
- [Text2Human: Text-Driven Controllable Human Image Generation](https://mlsanity.com/paper/2205.15996/) (2022)
- [MV-TON: Memory-based Video Virtual Try-on network](https://mlsanity.com/paper/2108.07502/) (2021)
- [Deep learning-based person re-identification methods: A survey and outlook of recent works](https://mlsanity.com/paper/2110.04764/) (2021)
- [Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling](https://mlsanity.com/paper/2103.14338/) (2021)
- [Discovering Distinctive "Semantics" in Super-Resolution Networks](https://mlsanity.com/paper/2108.00406/) (2021)
- [Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning](https://mlsanity.com/paper/2502.12425/) (2025)
- [InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation](https://mlsanity.com/paper/2101.03049/) (2021)
- [AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints](https://mlsanity.com/paper/2205.10636/) (2022)

## Abstract (arXiv)

Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such images based on a novel, two-stage reconstruction pipeline that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time. First, a multi-branched reconstruction network is proposed to disentangle and encode the three factors into embedding features, which are then combined to re-compose the input image itself. Second, three corresponding mapping functions are learned in an adversarial manner in order to map Gaussian noise to the learned embedding feature space, for each factor respectively. Using the proposed framework, we can manipulate the foreground, background and pose of the input image, and also sample new embedding features to generate such targeted manipulations, that provide more control over the generation process. Experiments on Market-1501 and Deepfashion datasets show that our model does not only generate realistic person images with new foregrounds, backgrounds and poses, but also manipulates the generated factors and interpolates the in-between states. Another set of experiments on Market-1501 shows that our model can also be beneficial for the person re-identification task.