# Learning Human Mesh Recovery in 3D Scenes

arXiv: https://arxiv.org/abs/2306.03847 · HTML: https://mlsanity.com/paper/2306.03847/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 41 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [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)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://mlsanity.com/paper/2011.13005/) (2020)
- [Convolutional Mesh Regression for Single-Image Human Shape Reconstruction](https://mlsanity.com/paper/1905.03244/) (2019)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [Embodied Hands: Modeling and Capturing Hands and Bodies Together](https://mlsanity.com/paper/2201.02610/) (2022)
- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [Populating 3D Scenes by Learning Human-Scene Interaction](https://mlsanity.com/paper/2012.11581/) (2020)
- [Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild](https://mlsanity.com/paper/2007.15649/) (2020)
- [SPEC: Seeing People in the Wild with an Estimated Camera](https://mlsanity.com/paper/2110.00620/) (2021)
- [Generating 3D People in Scenes without People](https://mlsanity.com/paper/1912.02923/) (2019)
- [Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation](https://mlsanity.com/paper/2004.03686/) (2020)
- [Learning Motion Priors for 4D Human Body Capture in 3D Scenes](https://mlsanity.com/paper/2108.10399/) (2021)
- [Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields](https://mlsanity.com/paper/2207.13807/) (2022)
- [TorchSparse: Efficient Point Cloud Inference Engine](https://mlsanity.com/paper/2204.10319/) (2022)
- [Holistic 3D Human and Scene Mesh Estimation from Single View Images](https://mlsanity.com/paper/2012.01591/) (2020)
- [SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation](https://mlsanity.com/paper/2008.11469/) (2020)
- [PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time](https://mlsanity.com/paper/2008.08880/) (2020)
- [HULC: 3D Human Motion Capture with Pose Manifold Sampling and Dense Contact Guidance](https://mlsanity.com/paper/2205.05677/) (2022)

## Built on by (most cited first, 13 of 13)

- [Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors](https://mlsanity.com/paper/2312.02196/) (2023)
- [Synergistic Global-space Camera and Human Reconstruction from Videos](https://mlsanity.com/paper/2405.14855/) (2024)
- [EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling](https://mlsanity.com/paper/2412.10235/) (2024)
- [UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues](https://mlsanity.com/paper/2404.14634/) (2024)
- [Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery](https://mlsanity.com/paper/2403.09063/) (2024)
- [Human-Aware 3D Scene Generation with Spatially-constrained Diffusion Models](https://mlsanity.com/paper/2406.18159/) (2024)
- [mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction](https://mlsanity.com/paper/2503.02375/) (2025)
- [SkelFormer: Markerless 3D Pose and Shape Estimation using Skeletal Transformers](https://mlsanity.com/paper/2404.12625/) (2024)
- [Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Models](https://mlsanity.com/paper/2410.00309/) (2024)
- [Mocap-2-to-3: Multi-view Lifting for Monocular Motion Recovery with 2D Pretraining](https://mlsanity.com/paper/2503.03222/) (2025)
- [Avatar4D: Synthesizing Domain-Specific 4D Humans for Real-World Pose Estimation](https://mlsanity.com/paper/2512.16199/) (2025)
- [InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery](https://mlsanity.com/paper/2605.04554/) (2026)
- [Efficient Human-Contact Representation for Human-Scene Interaction](https://mlsanity.com/paper/2608.09388/) (2026)

## Abstract (arXiv)

We present a novel method for recovering the absolute pose and shape of a human in a pre-scanned scene given a single image. Unlike previous methods that perform sceneaware mesh optimization, we propose to first estimate absolute position and dense scene contacts with a sparse 3D CNN, and later enhance a pretrained human mesh recovery network by cross-attention with the derived 3D scene cues. Joint learning on images and scene geometry enables our method to reduce the ambiguity caused by depth and occlusion, resulting in more reasonable global postures and contacts. Encoding scene-aware cues in the network also allows the proposed method to be optimization-free, and opens up the opportunity for real-time applications. The experiments show that the proposed network is capable of recovering accurate and physically-plausible meshes by a single forward pass and outperforms state-of-the-art methods in terms of both accuracy and speed.