# SMPLy Benchmarking 3D Human Pose Estimation in the Wild

arXiv: https://arxiv.org/abs/2012.02743 · HTML: https://mlsanity.com/paper/2012.02743/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2020.

## Built on by (most cited first, 16 of 16)

- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [Probabilistic Modeling for Human Mesh Recovery](https://mlsanity.com/paper/2108.11944/) (2021)
- [SPEC: Seeing People in the Wild with an Estimated Camera](https://mlsanity.com/paper/2110.00620/) (2021)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Playing for 3D Human Recovery](https://mlsanity.com/paper/2110.07588/) (2021)
- [Score-Guided Diffusion for 3D Human Recovery](https://mlsanity.com/paper/2403.09623/) (2024)
- [Learnable human mesh triangulation for 3D human pose and shape estimation](https://mlsanity.com/paper/2208.11251/) (2022)
- [PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling](https://mlsanity.com/paper/2208.10211/) (2022)
- [Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics](https://mlsanity.com/paper/2409.04033/) (2024)
- [MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision](https://mlsanity.com/paper/2108.04869/) (2021)
- [Leveraging MoCap Data for Human Mesh Recovery](https://mlsanity.com/paper/2110.09243/) (2021)
- [Crowd3D: Towards Hundreds of People Reconstruction from a Single Image](https://mlsanity.com/paper/2301.09376/) (2023)
- [WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users](https://mlsanity.com/paper/2404.17063/) (2024)
- [LPSNet: End-to-End Human Pose and Shape Estimation with Lensless Imaging](https://mlsanity.com/paper/2404.01941/) (2024)
- [SHARE: Single-view Human Adversarial REconstruction](https://mlsanity.com/paper/2401.00343/) (2023)

## Abstract (arXiv)

Predicting 3D human pose from images has seen great recent improvements. Novel approaches that can even predict both pose and shape from a single input image have been introduced, often relying on a parametric model of the human body such as SMPL. While qualitative results for such methods are often shown for images captured in-the-wild, a proper benchmark in such conditions is still missing, as it is cumbersome to obtain ground-truth 3D poses elsewhere than in a motion capture room. This paper presents a pipeline to easily produce and validate such a dataset with accurate ground-truth, with which we benchmark recent 3D human pose estimation methods in-the-wild. We make use of the recently introduced Mannequin Challenge dataset which contains in-the-wild videos of people frozen in action like statues and leverage the fact that people are static and the camera moving to accurately fit the SMPL model on the sequences. A total of 24,428 frames with registered body models are then selected from 567 scenes at almost no cost, using only online RGB videos. We benchmark state-of-the-art SMPL-based human pose estimation methods on this dataset. Our results highlight that challenges remain, in particular for difficult poses or for scenes where the persons are partially truncated or occluded.