# UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

arXiv: https://arxiv.org/abs/2110.15267 · HTML: https://mlsanity.com/paper/2110.15267/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 28 Oct 2021.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [Synthetic Data for Deep Learning](https://mlsanity.com/paper/1909.11512/) (2019)
- [Dense Pose Transfer](https://mlsanity.com/paper/1809.01995/) (2018)
- [Dissecting Person Re-identification from the Viewpoint of Viewpoint](https://mlsanity.com/paper/1812.02162/) (2018)
- [Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World](https://mlsanity.com/paper/1803.08319/) (2018)
- [Continuous Surface Embeddings](https://mlsanity.com/paper/2011.12438/) (2020)
- [Photo Wake-Up: 3D Character Animation from a Single Photo](https://mlsanity.com/paper/1812.02246/) (2018)
- [Parsing R-CNN for Instance-Level Human Analysis](https://mlsanity.com/paper/1811.12596/) (2018)
- [TexturePose: Supervising Human Mesh Estimation with Texture Consistency](https://mlsanity.com/paper/1910.11322/) (2019)
- [Domain Adaptation through Synthesis for Unsupervised Person Re-identification](https://mlsanity.com/paper/1804.10094/) (2018)
- [DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild](https://mlsanity.com/paper/1803.02188/) (2018)
- [M2E-Try On Net: Fashion from Model to Everyone](https://mlsanity.com/paper/1811.08599/) (2018)
- [Transferring Dense Pose to Proximal Animal Classes](https://mlsanity.com/paper/2003.00080/) (2020)
- [Soccer on Your Tabletop](https://mlsanity.com/paper/1806.00890/) (2018)
- [WAS-VTON: Warping Architecture Search for Virtual Try-on Network](https://mlsanity.com/paper/2108.00386/) (2021)
- [Slim DensePose: Thrifty Learning from Sparse Annotations and Motion Cues](https://mlsanity.com/paper/1906.05706/) (2019)

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

- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [HSPACE: Synthetic Parametric Humans Animated in Complex Environments](https://mlsanity.com/paper/2112.12867/) (2021)
- [BodyMap: Learning Full-Body Dense Correspondence Map](https://mlsanity.com/paper/2205.09111/) (2022)
- [Human Image Generation: A Comprehensive Survey](https://mlsanity.com/paper/2212.08896/) (2022)
- [TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates](https://mlsanity.com/paper/2204.03671/) (2022)
- [Normal-guided Garment UV Prediction for Human Re-texturing](https://mlsanity.com/paper/2303.06504/) (2023)
- [Pattern Guided UV Recovery for Realistic Video Garment Texturing](https://mlsanity.com/paper/2407.10137/) (2024)
- [Noise-in, Bias-out: Balanced and Real-time MoCap Solving](https://mlsanity.com/paper/2309.14330/) (2023)
- [PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models](https://mlsanity.com/paper/2603.28763/) (2026)

## Abstract (arXiv)

Recovering dense human poses from images plays a critical role in establishing an image-to-surface correspondence between RGB images and the 3D surface of the human body, serving the foundation of rich real-world applications, such as virtual humans, monocular-to-3d reconstruction. However, the popular DensePose-COCO dataset relies on a sophisticated manual annotation system, leading to severe limitations in acquiring the denser and more accurate annotated pose resources. In this work, we introduce a new 3D human-body model with a series of decoupled parameters that could freely control the generation of the body. Furthermore, we build a data generation system based on this decoupling 3D model, and construct an ultra dense synthetic benchmark UltraPose, containing around 1.3 billion corresponding points. Compared to the existing manually annotated DensePose-COCO dataset, the synthetic UltraPose has ultra dense image-to-surface correspondences without annotation cost and error. Our proposed UltraPose provides the largest benchmark and data resources for lifting the model capability in predicting more accurate dense poses. To promote future researches in this field, we also propose a transformer-based method to model the dense correspondence between 2D and 3D worlds. The proposed model trained on synthetic UltraPose can be applied to real-world scenarios, indicating the effectiveness of our benchmark and model.