# MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation

arXiv: https://arxiv.org/abs/2007.07227 · HTML: https://mlsanity.com/paper/2007.07227/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2020.

## Built on by (most cited first, 30 of 35)

- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors](https://mlsanity.com/paper/2103.17265/) (2021)
- [Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2407.07532/) (2024)
- [Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats](https://mlsanity.com/paper/2212.14474/) (2022)
- [RoHM: Robust Human Motion Reconstruction via Diffusion](https://mlsanity.com/paper/2401.08570/) (2024)
- [Embodied Scene-aware Human Pose Estimation](https://mlsanity.com/paper/2206.09106/) (2022)
- [Monocular 3D Human Pose Estimation for Sports Broadcasts using Partial Sports Field Registration](https://mlsanity.com/paper/2304.04437/) (2023)
- [Improved Trajectory Reconstruction for Markerless Pose Estimation](https://mlsanity.com/paper/2303.02413/) (2023)
- [Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement](https://mlsanity.com/paper/2210.13529/) (2022)
- [VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data](https://mlsanity.com/paper/2207.09949/) (2022)
- [Markerless Motion Capture and Biomechanical Analysis Pipeline](https://mlsanity.com/paper/2303.10654/) (2023)
- [3D Human Pose Estimation Using M"obius Graph Convolutional Networks](https://mlsanity.com/paper/2203.10554/) (2022)
- [Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs](https://mlsanity.com/paper/2502.05641/) (2025)
- [Geometric Neural Distance Fields for Learning Human Motion Priors](https://mlsanity.com/paper/2509.09667/) (2025)
- [Multi-view Pose Fusion for Occlusion-Aware 3D Human Pose Estimation](https://mlsanity.com/paper/2408.15810/) (2024)
- [MoFM: A Large-Scale Human Motion Foundation Model](https://mlsanity.com/paper/2502.05432/) (2025)
- [HumanScore: Benchmarking Human Motions in Generated Videos](https://mlsanity.com/paper/2604.20157/) (2026)
- [Video alignment using unsupervised learning of local and global features](https://mlsanity.com/paper/2304.06841/) (2023)
- [Adversarially-Refined VQ-GAN with Dense Motion Tokenization for Spatio-Temporal Heatmaps](https://mlsanity.com/paper/2509.19252/) (2025)
- [A Review on Human Pose Estimation](https://mlsanity.com/paper/2110.06877/) (2021)
- [Strengths and Weaknesses of 3D Pose Estimation and Inertial Motion Capture System for Movement Therapy](https://mlsanity.com/paper/2306.06117/) (2023)
- [SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data Augmentation](https://mlsanity.com/paper/2312.10195/) (2023)
- [D-PoSE: Depth as an Intermediate Representation for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2410.04889/) (2024)
- [Acquisition of high-quality images for camera calibration in robotics applications via speech prompts](https://mlsanity.com/paper/2504.11031/) (2025)
- [UPTor: Unified 3D Human Pose Dynamics and Trajectory Prediction for Human-Robot Interaction](https://mlsanity.com/paper/2505.14866/) (2025)
- [Systematic Comparison of Projection Methods for Monocular 3D Human Pose Estimation on Fisheye Images](https://mlsanity.com/paper/2506.19747/) (2025)
- [How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?](https://mlsanity.com/paper/2506.20795/) (2025)
- [Monocular Markerless Motion Capture Enables Quantitative Assessment of Upper Extremity Reachable Workspace](https://mlsanity.com/paper/2602.13176/) (2026)
- [Intelligent Image Sensing for Crime Analysis: A ML Approach towards Enhanced Violence Detection and Investigation](https://mlsanity.com/paper/2506.13910/) (2025)
- [UnrealPose: Leveraging Game Engine Kinematics for Large-Scale Synthetic Human Pose Data](https://mlsanity.com/paper/2601.00991/) (2026)

## Abstract (arXiv)

Heatmap representations have formed the basis of human pose estimation systems for many years, and their extension to 3D has been a fruitful line of recent research. This includes 2.5D volumetric heatmaps, whose X and Y axes correspond to image space and Z to metric depth around the subject. To obtain metric-scale predictions, 2.5D methods need a separate post-processing step to resolve scale ambiguity. Further, they cannot localize body joints outside the image boundaries, leading to incomplete estimates for truncated images. To address these limitations, we propose metric-scale truncation-robust (MeTRo) volumetric heatmaps, whose dimensions are all defined in metric 3D space, instead of being aligned with image space. This reinterpretation of heatmap dimensions allows us to directly estimate complete, metric-scale poses without test-time knowledge of distance or relying on anthropometric heuristics, such as bone lengths. To further demonstrate the utility our representation, we present a differentiable combination of our 3D metric-scale heatmaps with 2D image-space ones to estimate absolute 3D pose (our MeTRAbs architecture). We find that supervision via absolute pose loss is crucial for accurate non-root-relative localization. Using a ResNet-50 backbone without further learned layers, we obtain state-of-the-art results on Human3.6M, MPI-INF-3DHP and MuPoTS-3D. Our code will be made publicly available to facilitate further research.