# ARTS: Semi-Analytical Regressor using Disentangled Skeletal Representations for Human Mesh Recovery from Videos

arXiv: https://arxiv.org/abs/2410.15582 · HTML: https://mlsanity.com/paper/2410.15582/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 7 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 5 of 5)

- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [Conditional Directed Graph Convolution for 3D Human Pose Estimation](https://mlsanity.com/paper/2107.07797/) (2021)
- [PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos](https://mlsanity.com/paper/2103.09009/) (2021)
- [A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose](https://mlsanity.com/paper/2111.12696/) (2021)
- [ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation](https://mlsanity.com/paper/2403.01345/) (2024)

## Built on by (most cited first, 4 of 4)

- [Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning](https://mlsanity.com/paper/2508.10897/) (2025)
- [Towards Geometry-Aware and Motion-Guided Video Human Mesh Recovery](https://mlsanity.com/paper/2601.21376/) (2026)
- [Depth-Guided Metric-Aware Temporal Consistency for Monocular Video Human Mesh Recovery](https://mlsanity.com/paper/2602.04257/) (2026)
- [MoPO: Incorporating Motion Prior for Occluded Human Mesh Recovery](https://mlsanity.com/paper/2605.09856/) (2026)

## Abstract (arXiv)

Although existing video-based 3D human mesh recovery methods have made significant progress, simultaneously estimating human pose and shape from low-resolution image features limits their performance. These image features lack sufficient spatial information about the human body and contain various noises (e.g., background, lighting, and clothing), which often results in inaccurate pose and inconsistent motion. Inspired by the rapid advance in human pose estimation, we discover that compared to image features, skeletons inherently contain accurate human pose and motion. Therefore, we propose a novel semiAnalytical Regressor using disenTangled Skeletal representations for human mesh recovery from videos, called ARTS. Specifically, a skeleton estimation and disentanglement module is proposed to estimate the 3D skeletons from a video and decouple them into disentangled skeletal representations (i.e., joint position, bone length, and human motion). Then, to fully utilize these representations, we introduce a semi-analytical regressor to estimate the parameters of the human mesh model. The regressor consists of three modules: Temporal Inverse Kinematics (TIK), Bone-guided Shape Fitting (BSF), and Motion-Centric Refinement (MCR). TIK utilizes joint position to estimate initial pose parameters and BSF leverages bone length to regress bone-aligned shape parameters. Finally, MCR combines human motion representation with image features to refine the initial human model parameters. Extensive experiments demonstrate that our ARTS surpasses existing state-of-the-art video-based methods in both per-frame accuracy and temporal consistency on popular benchmarks: 3DPW, MPI-INF-3DHP, and Human3.6M. Code is available at https://github.com/TangTao-PKU/ARTS.