# Exploiting temporal context for 3D human pose estimation in the wild

arXiv: https://arxiv.org/abs/1905.04266 · HTML: https://mlsanity.com/paper/1905.04266/

## Key facts

- Cited by 110 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2019.

## Built on by (most cited first, 30 of 110)

- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [Probabilistic Modeling for Human Mesh Recovery](https://mlsanity.com/paper/2108.11944/) (2021)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [Decoupling Human and Camera Motion from Videos in the Wild](https://mlsanity.com/paper/2302.12827/) (2023)
- [SPEC: Seeing People in the Wild with an Estimated Camera](https://mlsanity.com/paper/2110.00620/) (2021)
- [SimPoE: Simulated Character Control for 3D Human Pose Estimation](https://mlsanity.com/paper/2104.00683/) (2021)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Learning Motion Priors for 4D Human Body Capture in 3D Scenes](https://mlsanity.com/paper/2108.10399/) (2021)
- [TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement](https://mlsanity.com/paper/2205.07982/) (2022)
- [Playing for 3D Human Recovery](https://mlsanity.com/paper/2110.07588/) (2021)
- [Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation](https://mlsanity.com/paper/2109.02303/) (2021)
- [DOVE: Learning Deformable 3D Objects by Watching Videos](https://mlsanity.com/paper/2107.10844/) (2021)
- [Towards unconstrained joint hand-object reconstruction from RGB videos](https://mlsanity.com/paper/2108.07044/) (2021)
- [Estimating Egocentric 3D Human Pose in Global Space](https://mlsanity.com/paper/2104.13454/) (2021)
- [Occluded Human Mesh Recovery](https://mlsanity.com/paper/2203.13349/) (2022)
- [THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers](https://mlsanity.com/paper/2106.09336/) (2021)
- [HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery](https://mlsanity.com/paper/2304.05690/) (2023)
- [RoHM: Robust Human Motion Reconstruction via Diffusion](https://mlsanity.com/paper/2401.08570/) (2024)
- [Reconstructing 3D Human Pose by Watching Humans in the Mirror](https://mlsanity.com/paper/2104.00340/) (2021)
- [GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human Pose Estimation from Monocular Video](https://mlsanity.com/paper/2307.05853/) (2023)
- [ReFit: Recurrent Fitting Network for 3D Human Recovery](https://mlsanity.com/paper/2308.11184/) (2023)
- [Body Meshes as Points](https://mlsanity.com/paper/2105.02467/) (2021)
- [3D Human Mesh Estimation from Virtual Markers](https://mlsanity.com/paper/2303.11726/) (2023)
- [Generative Proxemics: A Prior for 3D Social Interaction from Images](https://mlsanity.com/paper/2306.09337/) (2023)
- [D&D: Learning Human Dynamics from Dynamic Camera](https://mlsanity.com/paper/2209.08790/) (2022)

## Abstract (arXiv)

We present a bundle-adjustment-based algorithm for recovering accurate 3D human pose and meshes from monocular videos. Unlike previous algorithms which operate on single frames, we show that reconstructing a person over an entire sequence gives extra constraints that can resolve ambiguities. This is because videos often give multiple views of a person, yet the overall body shape does not change and 3D positions vary slowly. Our method improves not only on standard mocap-based datasets like Human 3.6M -- where we show quantitative improvements -- but also on challenging in-the-wild datasets such as Kinetics. Building upon our algorithm, we present a new dataset of more than 3 million frames of YouTube videos from Kinetics with automatically generated 3D poses and meshes. We show that retraining a single-frame 3D pose estimator on this data improves accuracy on both real-world and mocap data by evaluating on the 3DPW and HumanEVA datasets.