# Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers

arXiv: https://arxiv.org/abs/2207.13820 · HTML: https://mlsanity.com/paper/2207.13820/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 50 references that are in the map.
- First posted on arXiv 27 Jul 2022.

## Builds on (most cited first, 30 of 38)

- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [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)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [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)
- [End-to-End Video Instance Segmentation with Transformers](https://mlsanity.com/paper/2011.14503/) (2020)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [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)
- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [Convolutional Mesh Regression for Single-Image Human Shape Reconstruction](https://mlsanity.com/paper/1905.03244/) (2019)
- [Generating 3D faces using Convolutional Mesh Autoencoders](https://mlsanity.com/paper/1807.10267/) (2018)
- [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)
- [Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose](https://mlsanity.com/paper/2008.09047/) (2020)
- [Learning to Estimate 3D Human Pose and Shape from a Single Color Image](https://mlsanity.com/paper/1805.04092/) (2018)
- [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)
- [HOTR: End-to-End Human-Object Interaction Detection with Transformers](https://mlsanity.com/paper/2104.13682/) (2021)

## Built on by (most cited first, 30 of 81)

- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild](https://mlsanity.com/paper/2308.16894/) (2023)
- [Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering](https://mlsanity.com/paper/2312.11360/) (2023)
- [Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2407.07532/) (2024)
- [RoHM: Robust Human Motion Reconstruction via Diffusion](https://mlsanity.com/paper/2401.08570/) (2024)
- [Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba](https://mlsanity.com/paper/2407.09646/) (2024)
- [3D Human Mesh Estimation from Virtual Markers](https://mlsanity.com/paper/2303.11726/) (2023)
- [AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2403.17934/) (2024)
- [TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer](https://mlsanity.com/paper/2211.10705/) (2022)
- [Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction](https://mlsanity.com/paper/2303.13796/) (2023)
- [Score-Guided Diffusion for 3D Human Recovery](https://mlsanity.com/paper/2403.09623/) (2024)
- [Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views](https://mlsanity.com/paper/2304.06024/) (2023)
- [POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery](https://mlsanity.com/paper/2303.13357/) (2023)
- [Distribution-Aligned Diffusion for Human Mesh Recovery](https://mlsanity.com/paper/2308.13369/) (2023)
- [A Simple Baseline for Efficient Hand Mesh Reconstruction](https://mlsanity.com/paper/2403.01813/) (2024)
- [Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video](https://mlsanity.com/paper/2308.10305/) (2023)
- [Sampling is Matter: Point-guided 3D Human Mesh Reconstruction](https://mlsanity.com/paper/2304.09502/) (2023)
- [CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer](https://mlsanity.com/paper/2311.06443/) (2023)
- [Hulk: A Universal Knowledge Translator for Human-Centric Tasks](https://mlsanity.com/paper/2312.01697/) (2023)
- [Reconstructing Interacting Hands with Interaction Prior from Monocular Images](https://mlsanity.com/paper/2308.14082/) (2023)
- [SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens](https://mlsanity.com/paper/2411.19824/) (2024)
- [BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos](https://mlsanity.com/paper/2501.07800/) (2025)
- [Complementing Event Streams and RGB Frames for Hand Mesh Reconstruction](https://mlsanity.com/paper/2403.07346/) (2024)
- [MEGA: Masked Generative Autoencoder for Human Mesh Recovery](https://mlsanity.com/paper/2405.18839/) (2024)
- [WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation](https://mlsanity.com/paper/2501.02771/) (2025)
- [VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space](https://mlsanity.com/paper/2312.08291/) (2023)
- [MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction](https://mlsanity.com/paper/2211.13357/) (2022)
- [Deep learning for 3D human pose estimation and mesh recovery: A survey](https://mlsanity.com/paper/2402.18844/) (2024)

## Abstract (arXiv)

Transformer encoder architectures have recently achieved state-of-the-art results on monocular 3D human mesh reconstruction, but they require a substantial number of parameters and expensive computations. Due to the large memory overhead and slow inference speed, it is difficult to deploy such models for practical use. In this paper, we propose a novel transformer encoder-decoder architecture for 3D human mesh reconstruction from a single image, called FastMETRO. We identify the performance bottleneck in the encoder-based transformers is caused by the token design which introduces high complexity interactions among input tokens. We disentangle the interactions via an encoder-decoder architecture, which allows our model to demand much fewer parameters and shorter inference time. In addition, we impose the prior knowledge of human body's morphological relationship via attention masking and mesh upsampling operations, which leads to faster convergence with higher accuracy. Our FastMETRO improves the Pareto-front of accuracy and efficiency, and clearly outperforms image-based methods on Human3.6M and 3DPW. Furthermore, we validate its generalizability on FreiHAND.