# SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videos

arXiv: https://arxiv.org/abs/2512.08406 · HTML: https://mlsanity.com/paper/2512.08406/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 18 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Builds on (most cited first, 16 of 16)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model](https://mlsanity.com/paper/2207.07115/) (2022)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [Learning to Estimate 3D Human Pose and Shape from a Single Color Image](https://mlsanity.com/paper/1805.04092/) (2018)
- [Putting the Object Back into Video Object Segmentation](https://mlsanity.com/paper/2310.12982/) (2023)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation](https://mlsanity.com/paper/2404.16752/) (2024)
- [PromptHMR: Promptable Human Mesh Recovery](https://mlsanity.com/paper/2504.06397/) (2025)
- [Using Diffusion Priors for Video Amodal Segmentation](https://mlsanity.com/paper/2412.04623/) (2024)
- [MEGA: Masked Generative Autoencoder for Human Mesh Recovery](https://mlsanity.com/paper/2405.18839/) (2024)

## Built on by (most cited first, 8 of 8)

- [EgoExo-WM: Unlocking Exo Video for Ego World Models](https://mlsanity.com/paper/2605.15477/) (2026)
- [SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework](https://mlsanity.com/paper/2605.20373/) (2026)
- [SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild](https://mlsanity.com/paper/2605.07604/) (2026)
- [SAM4Dcap: Training-free Biomechanical Twin System from Monocular Video](https://mlsanity.com/paper/2602.13760/) (2026)
- [MHRGait: Gait Recognition from Momentum Human Rig Pose](https://mlsanity.com/paper/2607.29083/) (2026)
- [Towards Automated Initial Probe Placement in Transthoracic Teleultrasound Using Human Mesh and Skeleton Recovery](https://mlsanity.com/paper/2603.11257/) (2026)
- [AnyAct: Towards Human Reenactment of Character Motion From Video](https://mlsanity.com/paper/2605.15497/) (2026)
- [FlowDance: Music-Driven Dance Video Generation with Parallel Pose and RGB Streams](https://mlsanity.com/paper/2608.15818/) (2026)

## Abstract (arXiv)

Human Mesh Recovery (HMR) aims to reconstruct 3D human pose and shape from 2D observations and is fundamental to human-centric understanding in real-world scenarios. While recent image-based HMR methods such as SAM 3D Body achieve strong robustness on in-the-wild images, they rely on per-frame inference when applied to videos, leading to temporal inconsistency and degraded performance under occlusions. We address these issues without extra training by leveraging the inherent human continuity in videos. We propose SAM-Body4D, a training-free framework for temporally consistent and occlusion-robust HMR from videos. We first generate identity-consistent masklets using a promptable video segmentation model, then refine them with an Occlusion-Aware module to recover missing regions. The refined masklets guide SAM 3D Body to produce consistent full-body mesh trajectories, while a padding-based parallel strategy enables efficient multi-human inference. Experimental results demonstrate that SAM-Body4D achieves improved temporal stability and robustness in challenging in-the-wild videos, without any retraining. Our code and demo are available at: https://github.com/gaomingqi/sam-body4d.