# Shape-Aware Human Pose and Shape Reconstruction Using Multi-View Images

arXiv: https://arxiv.org/abs/1908.09464 · HTML: https://mlsanity.com/paper/1908.09464/

## Key facts

- Cited by 28 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 26 Aug 2019.

## Built on by (most cited first, 28 of 28)

- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Rendering](https://mlsanity.com/paper/2106.03798/) (2021)
- [Conditional Directed Graph Convolution for 3D Human Pose Estimation](https://mlsanity.com/paper/2107.07797/) (2021)
- [Accurate 3D Body Shape Regression using Metric and Semantic Attributes](https://mlsanity.com/paper/2206.07036/) (2022)
- [Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild](https://mlsanity.com/paper/2103.10978/) (2021)
- [POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture](https://mlsanity.com/paper/2103.15331/) (2021)
- [BEDLAM2.0: Synthetic Humans and Cameras in Motion](https://mlsanity.com/paper/2511.14394/) (2025)
- [SHARP: Shape-Aware Reconstruction of People in Loose Clothing](https://mlsanity.com/paper/2205.11948/) (2022)
- [AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2201.08093/) (2022)
- [Delving Deep into Pixel Alignment Feature for Accurate Multi-view Human Mesh Recovery](https://mlsanity.com/paper/2301.06020/) (2023)
- [Progressive Multi-view Human Mesh Recovery with Self-Supervision](https://mlsanity.com/paper/2212.05223/) (2022)
- [GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data](https://mlsanity.com/paper/2411.18624/) (2024)
- [Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model](https://mlsanity.com/paper/2111.15404/) (2021)
- [Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery](https://mlsanity.com/paper/2204.01276/) (2022)
- [High-Resolution Volumetric Reconstruction for Clothed Humans](https://mlsanity.com/paper/2307.13282/) (2023)
- [MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction](https://mlsanity.com/paper/2403.05055/) (2024)
- [Human Mesh Recovery from Arbitrary Multi-view Images](https://mlsanity.com/paper/2403.12434/) (2024)
- [ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation](https://mlsanity.com/paper/2403.01345/) (2024)
- [Multi-view Human Body Mesh Translator](https://mlsanity.com/paper/2210.01886/) (2022)
- [Human Body Measurement Estimation with Adversarial Augmentation](https://mlsanity.com/paper/2210.05667/) (2022)
- [Simultaneously Recovering Multi-Person Meshes and Multi-View Cameras with Human Semantics](https://mlsanity.com/paper/2412.18785/) (2024)
- [MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames](https://mlsanity.com/paper/2204.11184/) (2022)
- [SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers](https://mlsanity.com/paper/2404.12625/) (2024)
- [HeatFormer: A Neural Optimizer for Multiview Human Mesh Recovery](https://mlsanity.com/paper/2412.04456/) (2024)
- [SHARE: Single-view Human Adversarial REconstruction](https://mlsanity.com/paper/2401.00343/) (2023)
- [Self-learning Canonical Space for Multi-view 3D Human Pose Estimation](https://mlsanity.com/paper/2403.12440/) (2024)
- [A Simple Strategy for Body Estimation from Partial-View Images](https://mlsanity.com/paper/2404.09301/) (2024)
- [Monocular Models are Strong Learners for Multi-View Human Mesh Recovery](https://mlsanity.com/paper/2603.20391/) (2026)

## Abstract (arXiv)

We propose a scalable neural network framework to reconstruct the 3D mesh of a human body from multi-view images, in the subspace of the SMPL model. Use of multi-view images can significantly reduce the projection ambiguity of the problem, increasing the reconstruction accuracy of the 3D human body under clothing. Our experiments show that this method benefits from the synthetic dataset generated from our pipeline since it has good flexibility of variable control and can provide ground-truth for validation. Our method outperforms existing methods on real-world images, especially on shape estimations.