# Adversarial Parametric Pose Prior

arXiv: https://arxiv.org/abs/2112.04203 · HTML: https://mlsanity.com/paper/2112.04203/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 8 Dec 2021.

## Builds on (most cited first, 23 of 23)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [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)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Unite the People: Closing the Loop Between 3D and 2D Human Representations](https://mlsanity.com/paper/1701.02468/) (2017)
- [Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation](https://mlsanity.com/paper/1808.05942/) (2018)
- [NASA: Neural Articulated Shape Approximation](https://mlsanity.com/paper/1912.03207/) (2019)
- [Coherent Reconstruction of Multiple Humans from a Single Image](https://mlsanity.com/paper/2006.08586/) (2020)
- [Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation](https://mlsanity.com/paper/2004.03686/) (2020)
- [Exploiting temporal context for 3D human pose estimation in the wild](https://mlsanity.com/paper/1905.04266/) (2019)
- [Contact and Human Dynamics from Monocular Video](https://mlsanity.com/paper/2007.11678/) (2020)
- [Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows](https://mlsanity.com/paper/2003.10350/) (2020)
- [Hierarchical Kinematic Human Mesh Recovery](https://mlsanity.com/paper/2003.04232/) (2020)
- [LIMP: Learning Latent Shape Representations with Metric Preservation Priors](https://mlsanity.com/paper/2003.12283/) (2020)
- [CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields](https://mlsanity.com/paper/2103.17269/) (2021)
- [TexturePose: Supervising Human Mesh Estimation with Texture Consistency](https://mlsanity.com/paper/1910.11322/) (2019)
- [Building Statistical Shape Spaces for 3D Human Modeling](https://mlsanity.com/paper/1503.05860/) (2015)
- [Everybody Is Unique: Towards Unbiased Human Mesh Recovery](https://mlsanity.com/paper/2107.06239/) (2021)

## Built on by (most cited first, 30 of 38)

- [CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation](https://mlsanity.com/paper/2208.00571/) (2022)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields](https://mlsanity.com/paper/2207.13807/) (2022)
- [DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models](https://mlsanity.com/paper/2211.16487/) (2022)
- [GFPose: Learning 3D Human Pose Prior with Gradient Fields](https://mlsanity.com/paper/2212.08641/) (2022)
- [Neural Sign Actors: A diffusion model for 3D sign language production from text](https://mlsanity.com/paper/2312.02702/) (2023)
- [DrapeNet: Garment Generation and Self-Supervised Draping](https://mlsanity.com/paper/2211.11277/) (2022)
- [Score-Guided Diffusion for 3D Human Recovery](https://mlsanity.com/paper/2403.09623/) (2024)
- [NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors](https://mlsanity.com/paper/2403.03122/) (2024)
- [Learning 3D Scene Priors with 2D Supervision](https://mlsanity.com/paper/2211.14157/) (2022)
- [Programmable Motion Generation for Open-Set Motion Control Tasks](https://mlsanity.com/paper/2405.19283/) (2024)
- [Modiff: Action-Conditioned 3D Motion Generation with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2301.03949/) (2023)
- [DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior](https://mlsanity.com/paper/2508.00599/) (2025)
- [MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering](https://mlsanity.com/paper/2403.18820/) (2024)
- [Bringing motion taxonomies to continuous domains via GPLVM on hyperbolic manifolds](https://mlsanity.com/paper/2210.01672/) (2022)
- [SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation](https://mlsanity.com/paper/2404.15276/) (2024)
- [Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior](https://mlsanity.com/paper/2310.20249/) (2023)
- [BodySLAM++: Fast and Tightly-Coupled Visual-Inertial Camera and Human Motion Tracking](https://mlsanity.com/paper/2309.01236/) (2023)
- [Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling](https://mlsanity.com/paper/2404.05675/) (2024)
- [KBody: Towards general, robust, and aligned monocular whole-body estimation](https://mlsanity.com/paper/2304.11542/) (2023)
- [Geometric Neural Distance Fields for Learning Human Motion Priors](https://mlsanity.com/paper/2509.09667/) (2025)
- [Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection](https://mlsanity.com/paper/2405.15939/) (2024)
- [DiffSurf: A Transformer-based Diffusion Model for Generating and Reconstructing 3D Surfaces in Pose](https://mlsanity.com/paper/2408.14860/) (2024)
- [PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF](https://mlsanity.com/paper/2312.14915/) (2023)
- [Personalized 3D Human Pose and Shape Refinement](https://mlsanity.com/paper/2403.11634/) (2024)
- [Multi-modal Pose Diffuser: A Multimodal Generative Conditional Pose Prior](https://mlsanity.com/paper/2410.14540/) (2024)
- [Recovering Complete Actions for Cross-dataset Skeleton Action Recognition](https://mlsanity.com/paper/2410.23641/) (2024)
- [MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction](https://mlsanity.com/paper/2507.15212/) (2025)
- [Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery](https://mlsanity.com/paper/2401.14121/) (2024)
- [MoManifold: Learning to Measure 3D Human Motion via Decoupled Joint Acceleration Manifolds](https://mlsanity.com/paper/2409.00736/) (2024)

## Abstract (arXiv)

The Skinned Multi-Person Linear (SMPL) model can represent a human body by mapping pose and shape parameters to body meshes. This has been shown to facilitate inferring 3D human pose and shape from images via different learning models. However, not all pose and shape parameter values yield physically-plausible or even realistic body meshes. In other words, SMPL is under-constrained and may thus lead to invalid results when used to reconstruct humans from images, either by directly optimizing its parameters, or by learning a mapping from the image to these parameters. In this paper, we therefore learn a prior that restricts the SMPL parameters to values that produce realistic poses via adversarial training. We show that our learned prior covers the diversity of the real-data distribution, facilitates optimization for 3D reconstruction from 2D keypoints, and yields better pose estimates when used for regression from images. We found that the prior based on spherical distribution gets the best results. Furthermore, in all these tasks, it outperforms the state-of-the-art VAE-based approach to constraining the SMPL parameters.