# MEGA: Masked Generative Autoencoder for Human Mesh Recovery

arXiv: https://arxiv.org/abs/2405.18839 · HTML: https://mlsanity.com/paper/2405.18839/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 82 of its 100 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 30 of 82)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [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 Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [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)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2011.14672/) (2020)
- [Convolutional Mesh Regression for Single-Image Human Shape Reconstruction](https://mlsanity.com/paper/1905.03244/) (2019)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)

## Built on by (most cited first, 14 of 14)

- [UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing](https://mlsanity.com/paper/2411.16781/) (2024)
- [SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos](https://mlsanity.com/paper/2512.08406/) (2025)
- [DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction](https://mlsanity.com/paper/2603.03265/) (2026)
- [VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery](https://mlsanity.com/paper/2602.19180/) (2026)
- [Masked Modeling for Human Motion Recovery Under Occlusions](https://mlsanity.com/paper/2601.16079/) (2026)
- [Pose-RFT: Enhancing MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning](https://mlsanity.com/paper/2508.07804/) (2025)
- [LieHMR: Autoregressive Human Mesh Recovery with SO(3) Diffusion](https://mlsanity.com/paper/2509.25739/) (2025)
- [On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation](https://mlsanity.com/paper/2510.12660/) (2025)
- [PHAC: Promptable Human Amodal Completion](https://mlsanity.com/paper/2603.14741/) (2026)
- [MoPO: Incorporating Motion Prior for Occluded Human Mesh Recovery](https://mlsanity.com/paper/2605.09856/) (2026)
- [FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery](https://mlsanity.com/paper/2605.14854/) (2026)
- [B'ezier Degradation Modeling for LiDAR-based Human Motion Capture](https://mlsanity.com/paper/2605.19620/) (2026)
- [MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery](https://mlsanity.com/paper/2609.10743/) (2026)
- [OmniPoser: Flexible Human Motion Recovery in the Wild with Masked Flow Matching](https://mlsanity.com/paper/2610.19857/) (2026)

## Abstract (arXiv)

Human Mesh Recovery (HMR) from a single RGB image is a highly ambiguous problem, as an infinite set of 3D interpretations can explain the 2D observation equally well. Nevertheless, most HMR methods overlook this issue and make a single prediction without accounting for this ambiguity. A few approaches generate a distribution of human meshes, enabling the sampling of multiple predictions; however, none of them is competitive with the latest single-output model when making a single prediction. This work proposes a new approach based on masked generative modeling. By tokenizing the human pose and shape, we formulate the HMR task as generating a sequence of discrete tokens conditioned on an input image. We introduce MEGA, a MaskEd Generative Autoencoder trained to recover human meshes from images and partial human mesh token sequences. Given an image, our flexible generation scheme allows us to predict a single human mesh in deterministic mode or to generate multiple human meshes in stochastic mode. Experiments on in-the-wild benchmarks show that MEGA achieves state-of-the-art performance in deterministic and stochastic modes, outperforming single-output and multi-output approaches.