# 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data

arXiv: https://arxiv.org/abs/2011.00980 · HTML: https://mlsanity.com/paper/2011.00980/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

## Built on by (most cited first, 30 of 50)

- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows](https://mlsanity.com/paper/2107.13788/) (2021)
- [DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models](https://mlsanity.com/paper/2211.16487/) (2022)
- [FLAG: Flow-based 3D Avatar Generation from Sparse Observations](https://mlsanity.com/paper/2203.05789/) (2022)
- [THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers](https://mlsanity.com/paper/2106.09336/) (2021)
- [NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2305.08590/) (2023)
- [Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape](https://mlsanity.com/paper/2308.11737/) (2023)
- [Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views](https://mlsanity.com/paper/2304.06024/) (2023)
- [3D-Aware Neural Body Fitting for Occlusion Robust 3D Human Pose Estimation](https://mlsanity.com/paper/2308.10123/) (2023)
- [Distribution-Aligned Diffusion for Human Mesh Recovery](https://mlsanity.com/paper/2308.13369/) (2023)
- [Sampling is Matter: Point-guided 3D Human Mesh Reconstruction](https://mlsanity.com/paper/2304.09502/) (2023)
- [HUM3DIL: Semi-supervised Multi-modal 3D Human Pose Estimation for Autonomous Driving](https://mlsanity.com/paper/2212.07729/) (2022)
- [POCO: 3D Pose and Shape Estimation with Confidence](https://mlsanity.com/paper/2308.12965/) (2023)
- [HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations](https://mlsanity.com/paper/2308.11261/) (2023)
- [Coarse-to-fine Animal Pose and Shape Estimation](https://mlsanity.com/paper/2111.08176/) (2021)
- [Learning to Fit Morphable Models](https://mlsanity.com/paper/2111.14824/) (2021)
- [Occluded Human Body Capture with Self-Supervised Spatial-Temporal Motion Prior](https://mlsanity.com/paper/2207.05375/) (2022)
- [Rendering Humans from Object-Occluded Monocular Videos](https://mlsanity.com/paper/2308.04622/) (2023)
- [MEGA: Masked Generative Autoencoder for Human Mesh Recovery](https://mlsanity.com/paper/2405.18839/) (2024)
- [VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space](https://mlsanity.com/paper/2312.08291/) (2023)
- [DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans](https://mlsanity.com/paper/2404.00485/) (2024)
- [Domain Adaptive 3D Pose Augmentation for In-the-wild Human Mesh Recovery](https://mlsanity.com/paper/2206.10457/) (2022)
- [Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence Learning](https://mlsanity.com/paper/2211.14052/) (2022)
- [Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation](https://mlsanity.com/paper/2208.00090/) (2022)
- [Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation](https://mlsanity.com/paper/2203.07697/) (2022)
- [Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstruction](https://mlsanity.com/paper/2308.00799/) (2023)
- [ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization](https://mlsanity.com/paper/2505.10250/) (2025)

## Abstract (arXiv)

We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views. In such cases, the visual evidence is usually insufficient to identify a 3D reconstruction uniquely, so we aim at recovering several plausible reconstructions compatible with the input data. We suggest that ambiguities can be modelled more effectively by parametrizing the possible body shapes and poses via a suitable 3D model, such as SMPL for humans. We propose to learn a multi-hypothesis neural network regressor using a best-of-M loss, where each of the M hypotheses is constrained to lie on a manifold of plausible human poses by means of a generative model. We show that our method outperforms alternative approaches in ambiguous pose recovery on standard benchmarks for 3D humans, and in heavily occluded versions of these benchmarks.