# Leveraging MoCap Data for Human Mesh Recovery

arXiv: https://arxiv.org/abs/2110.09243 · HTML: https://mlsanity.com/paper/2110.09243/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 50 references that are in the map.
- First posted on arXiv 18 Oct 2021.

## Builds on (most cited first, 30 of 42)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.03713/) (2020)
- [Convolutional Mesh Regression for Single-Image Human Shape Reconstruction](https://mlsanity.com/paper/1905.03244/) (2019)
- [Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose](https://mlsanity.com/paper/2008.09047/) (2020)
- [Monocular, One-stage, Regression of Multiple 3D People](https://mlsanity.com/paper/2008.12272/) (2020)
- [Unite the People: Closing the Loop Between 3D and 2D Human Representations](https://mlsanity.com/paper/1701.02468/) (2017)
- [Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB](https://mlsanity.com/paper/1712.03453/) (2017)
- [Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation](https://mlsanity.com/paper/1808.05942/) (2018)
- [Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video](https://mlsanity.com/paper/2011.08627/) (2020)
- [BodyNet: Volumetric Inference of 3D Human Body Shapes](https://mlsanity.com/paper/1804.04875/) (2018)
- [Exploiting temporal context for 3D human pose estimation in the wild](https://mlsanity.com/paper/1905.04266/) (2019)
- [Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs](https://mlsanity.com/paper/2003.00152/) (2020)
- [3D Human Motion Estimation via Motion Compression and Refinement](https://mlsanity.com/paper/2008.03789/) (2020)
- [Towards Accurate Markerless Human Shape and Pose Estimation over Time](https://mlsanity.com/paper/1707.07548/) (2017)

## Built on by (most cited first, 12 of 12)

- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting](https://mlsanity.com/paper/2210.10542/) (2022)
- [On the Benefits of 3D Pose and Tracking for Human Action Recognition](https://mlsanity.com/paper/2304.01199/) (2023)
- [PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling](https://mlsanity.com/paper/2208.10211/) (2022)
- [MEGA: Masked Generative Autoencoder for Human Mesh Recovery](https://mlsanity.com/paper/2405.18839/) (2024)
- [MASA: Motion-aware Masked Autoencoder with Semantic Alignment for Sign Language Recognition](https://mlsanity.com/paper/2405.20666/) (2024)
- [MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction](https://mlsanity.com/paper/2211.13357/) (2022)
- [Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2303.05370/) (2023)
- [HumanMM: Global Human Motion Recovery from Multi-shot Videos](https://mlsanity.com/paper/2503.07597/) (2025)
- [Multi-Human Mesh Recovery with Transformers](https://mlsanity.com/paper/2402.16806/) (2024)
- [HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task](https://mlsanity.com/paper/2406.01914/) (2024)
- [Temporally-consistent 3D Reconstruction of Birds](https://mlsanity.com/paper/2408.13629/) (2024)

## Abstract (arXiv)

Training state-of-the-art models for human body pose and shape recovery from images or videos requires datasets with corresponding annotations that are really hard and expensive to obtain. Our goal in this paper is to study whether poses from 3D Motion Capture (MoCap) data can be used to improve image-based and video-based human mesh recovery methods. We find that fine-tune image-based models with synthetic renderings from MoCap data can increase their performance, by providing them with a wider variety of poses, textures and backgrounds. In fact, we show that simply fine-tuning the batch normalization layers of the model is enough to achieve large gains. We further study the use of MoCap data for video, and introduce PoseBERT, a transformer module that directly regresses the pose parameters and is trained via masked modeling. It is simple, generic and can be plugged on top of any state-of-the-art image-based model in order to transform it in a video-based model leveraging temporal information. Our experimental results show that the proposed approaches reach state-of-the-art performance on various datasets including 3DPW, MPI-INF-3DHP, MuPoTS-3D, MCB and AIST. Test code and models will be available soon.