# UnitedHuman: Harnessing Multi-Source Data for High-Resolution Human Generation

arXiv: https://arxiv.org/abs/2309.14335 · HTML: https://mlsanity.com/paper/2309.14335/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 29 of 29)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization](https://mlsanity.com/paper/2103.16874/) (2021)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.09309/) (2020)
- [StyleGAN-Human: A Data-Centric Odyssey of Human Generation](https://mlsanity.com/paper/2204.11823/) (2022)
- [Look at Boundary: A Boundary-Aware Face Alignment Algorithm](https://mlsanity.com/paper/1805.10483/) (2018)
- [Progressive Pose Attention Transfer for Person Image Generation](https://mlsanity.com/paper/1904.03349/) (2019)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Person Image Synthesis via Denoising Diffusion Model](https://mlsanity.com/paper/2211.12500/) (2022)
- [XingGAN for Person Image Generation](https://mlsanity.com/paper/2007.09278/) (2020)
- [Any-resolution Training for High-resolution Image Synthesis](https://mlsanity.com/paper/2204.07156/) (2022)
- [Positional Encoding as Spatial Inductive Bias in GANs](https://mlsanity.com/paper/2012.05217/) (2020)
- [Exploring Dual-task Correlation for Pose Guided Person Image Generation](https://mlsanity.com/paper/2203.02910/) (2022)
- [InfinityGAN: Towards Infinite-Pixel Image Synthesis](https://mlsanity.com/paper/2104.03963/) (2021)
- [Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN](https://mlsanity.com/paper/2109.06166/) (2021)
- [InsetGAN for Full-Body Image Generation](https://mlsanity.com/paper/2203.07293/) (2022)
- [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)
- [Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis](https://mlsanity.com/paper/2204.11798/) (2022)
- [DART: Articulated Hand Model with Diverse Accessories and Rich Textures](https://mlsanity.com/paper/2210.07650/) (2022)
- [Arbitrary-Scale Image Synthesis](https://mlsanity.com/paper/2204.02273/) (2022)
- [Toward Spatially Unbiased Generative Models](https://mlsanity.com/paper/2108.01285/) (2021)
- [StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3](https://mlsanity.com/paper/2208.07862/) (2022)

## Built on by (most cited first, 9 of 9)

- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [Expressive Gaussian Human Avatars from Monocular RGB Video](https://mlsanity.com/paper/2407.03204/) (2024)
- [Human-Centric Foundation Models: Perception, Generation and Agentic Modeling](https://mlsanity.com/paper/2502.08556/) (2025)
- [MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention](https://mlsanity.com/paper/2503.08664/) (2025)
- [HumanGif: Single-View Human Diffusion with Generative Prior](https://mlsanity.com/paper/2502.12080/) (2025)
- [GroupDiff: Diffusion-based Group Portrait Editing](https://mlsanity.com/paper/2409.14379/) (2024)
- [Fashion Style Editing with Generative Human Prior](https://mlsanity.com/paper/2404.01984/) (2024)
- [Fashionability-Enhancing Outfit Image Editing with Conditional Diffusion Models](https://mlsanity.com/paper/2412.18421/) (2024)

## Abstract (arXiv)

Human generation has achieved significant progress. Nonetheless, existing methods still struggle to synthesize specific regions such as faces and hands. We argue that the main reason is rooted in the training data. A holistic human dataset inevitably has insufficient and low-resolution information on local parts. Therefore, we propose to use multi-source datasets with various resolution images to jointly learn a high-resolution human generative model. However, multi-source data inherently a) contains different parts that do not spatially align into a coherent human, and b) comes with different scales. To tackle these challenges, we propose an end-to-end framework, UnitedHuman, that empowers continuous GAN with the ability to effectively utilize multi-source data for high-resolution human generation. Specifically, 1) we design a Multi-Source Spatial Transformer that spatially aligns multi-source images to full-body space with a human parametric model. 2) Next, a continuous GAN is proposed with global-structural guidance and CutMix consistency. Patches from different datasets are then sampled and transformed to supervise the training of this scale-invariant generative model. Extensive experiments demonstrate that our model jointly learned from multi-source data achieves superior quality than those learned from a holistic dataset.