# TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation

arXiv: https://arxiv.org/abs/2404.16752 · HTML: https://mlsanity.com/paper/2404.16752/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 62 references that are in the map.
- First posted on arXiv 25 Apr 2024.

## Builds on (most cited first, 30 of 54)

- [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)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (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)
- [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)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [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)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [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, 30 of 95)

- [PromptHMR: Promptable Human Mesh Recovery](https://mlsanity.com/paper/2504.06397/) (2025)
- [SAM 3D Body: Robust Full-Body Human Mesh Recovery](https://mlsanity.com/paper/2602.15989/) (2026)
- [CameraHMR: Aligning People with Perspective](https://mlsanity.com/paper/2411.08128/) (2024)
- [Human3R: Everyone Everywhere All at Once](https://mlsanity.com/paper/2510.06219/) (2025)
- [Reconstructing People, Places, and Cameras](https://mlsanity.com/paper/2412.17806/) (2024)
- [PICO: Reconstructing 3D People In Contact with Objects](https://mlsanity.com/paper/2504.17695/) (2025)
- [InteractVLM: 3D Interaction Reasoning from 2D Foundational Models](https://mlsanity.com/paper/2504.05303/) (2025)
- [UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing](https://mlsanity.com/paper/2411.16781/) (2024)
- [Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis](https://mlsanity.com/paper/2412.08603/) (2024)
- [BioPose: Biomechanically-accurate 3D Pose Estimation from Monocular Videos](https://mlsanity.com/paper/2501.07800/) (2025)
- [MEGA: Masked Generative Autoencoder for Human Mesh Recovery](https://mlsanity.com/paper/2405.18839/) (2024)
- [Reconstructing 4D Spatial Intelligence: A Survey](https://mlsanity.com/paper/2507.21045/) (2025)
- [GST: Precise 3D Human Body from a Single Image with Gaussian Splatting Transformers](https://mlsanity.com/paper/2409.04196/) (2024)
- [Synergy and Synchrony in Couple Dances](https://mlsanity.com/paper/2409.04440/) (2024)
- [FIction: 4D Future Interaction Prediction from Video](https://mlsanity.com/paper/2412.00932/) (2024)
- [UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass](https://mlsanity.com/paper/2601.01222/) (2026)
- [ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos](https://mlsanity.com/paper/2504.13167/) (2025)
- [SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos](https://mlsanity.com/paper/2512.08406/) (2025)
- [Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images](https://mlsanity.com/paper/2410.03438/) (2024)
- [ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization](https://mlsanity.com/paper/2505.10250/) (2025)
- [M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction](https://mlsanity.com/paper/2512.12378/) (2025)
- [DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction](https://mlsanity.com/paper/2603.03265/) (2026)
- [DiSRT-In-Bed: Diffusion-Based Sim-to-Real Transfer Framework for In-Bed Human Mesh Recovery](https://mlsanity.com/paper/2504.03006/) (2025)
- [CondiMen: Conditional Multi-Person Mesh Recovery](https://mlsanity.com/paper/2412.13058/) (2024)
- [A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motions](https://mlsanity.com/paper/2412.17377/) (2024)
- [Motion Capture from Inertial and Vision Sensors](https://mlsanity.com/paper/2407.16341/) (2024)
- [Utilizing Uncertainty in 2D Pose Detectors for Probabilistic 3D Human Mesh Recovery](https://mlsanity.com/paper/2411.16289/) (2024)
- [Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded Dialogues](https://mlsanity.com/paper/2506.00958/) (2025)
- [MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images](https://mlsanity.com/paper/2506.09919/) (2025)
- [FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding](https://mlsanity.com/paper/2510.10868/) (2025)

## Abstract (arXiv)

We address the problem of regressing 3D human pose and shape from a single image, with a focus on 3D accuracy. The current best methods leverage large datasets of 3D pseudo-ground-truth (p-GT) and 2D keypoints, leading to robust performance. With such methods, we observe a paradoxical decline in 3D pose accuracy with increasing 2D accuracy. This is caused by biases in the p-GT and the use of an approximate camera projection model. We quantify the error induced by current camera models and show that fitting 2D keypoints and p-GT accurately causes incorrect 3D poses. Our analysis defines the invalid distances within which minimizing 2D and p-GT losses is detrimental. We use this to formulate a new loss Threshold-Adaptive Loss Scaling (TALS) that penalizes gross 2D and p-GT losses but not smaller ones. With such a loss, there are many 3D poses that could equally explain the 2D evidence. To reduce this ambiguity we need a prior over valid human poses but such priors can introduce unwanted bias. To address this, we exploit a tokenized representation of human pose and reformulate the problem as token prediction. This restricts the estimated poses to the space of valid poses, effectively providing a uniform prior. Extensive experiments on the EMDB and 3DPW datasets show that our reformulated keypoint loss and tokenization allows us to train on in-the-wild data while improving 3D accuracy over the state-of-the-art. Our models and code are available for research at https://tokenhmr.is.tue.mpg.de.