# Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation

arXiv: https://arxiv.org/abs/2512.16199 · HTML: https://mlsanity.com/paper/2512.16199/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 48 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 30 of 37)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2312.09228/) (2023)
- [Whole-Body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2007.11858/) (2020)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [Pose2Seg: Detection Free Human Instance Segmentation](https://mlsanity.com/paper/1803.10683/) (2018)
- [TokenPose: Learning Keypoint Tokens for Human Pose Estimation](https://mlsanity.com/paper/2104.03516/) (2021)
- [TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation](https://mlsanity.com/paper/2404.16752/) (2024)
- [SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos](https://mlsanity.com/paper/2204.06918/) (2022)
- [Seamless Human Motion Composition with Blended Positional Encodings](https://mlsanity.com/paper/2402.15509/) (2024)
- [The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation](https://mlsanity.com/paper/1911.07524/) (2019)
- [Playing for 3D Human Recovery](https://mlsanity.com/paper/2110.07588/) (2021)
- [LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds](https://mlsanity.com/paper/2503.10625/) (2025)
- [3DPeople: Modeling the Geometry of Dressed Humans](https://mlsanity.com/paper/1904.04571/) (2019)
- [IDOL: Instant Photorealistic 3D Human Creation from a Single Image](https://mlsanity.com/paper/2412.14963/) (2024)
- [AutoSoccerPose: Automated 3D posture Analysis of Soccer Shot Movements](https://mlsanity.com/paper/2405.12070/) (2024)

## Abstract (arXiv)

We present Avatar4D, a real-world transferable pipeline for generating customizable synthetic human motion datasets tailored to domain-specific applications. Unlike prior works, which focus on general, everyday motions and offer limited flexibility, our approach provides fine-grained control over body pose, appearance, camera viewpoint, and environmental context, without requiring any manual annotations. To validate the impact of Avatar4D, we focus on sports, where domain-specific human actions and movement patterns pose unique challenges for motion understanding. In this setting, we introduce Syn2Sport, a large-scale synthetic dataset spanning sports, including baseball and ice hockey. Avatar4D features high-fidelity 4D (3D geometry over time) human motion sequences with varying player appearances rendered in diverse environments. We benchmark several state-of-the-art pose estimation models on Syn2Sport and demonstrate their effectiveness for supervised learning, zero-shot transfer to real-world data, and generalization across sports. Furthermore, we evaluate how closely the generated synthetic data aligns with real-world datasets in feature space. Our results highlight the potential of such systems to generate scalable, controllable, and transferable human datasets for diverse domain-specific tasks without relying on domain-specific real data.