# Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations

arXiv: https://arxiv.org/abs/2001.01613 · HTML: https://mlsanity.com/paper/2001.01613/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2020.

## Built on by (most cited first, 12 of 12)

- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [Collaborative Regression of Expressive Bodies using Moderation](https://mlsanity.com/paper/2105.05301/) (2021)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Accurate 3D Body Shape Regression using Metric and Semantic Attributes](https://mlsanity.com/paper/2206.07036/) (2022)
- [Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction](https://mlsanity.com/paper/2103.16449/) (2021)
- [Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation](https://mlsanity.com/paper/2111.04017/) (2021)
- [Everybody Is Unique: Towards Unbiased Human Mesh Recovery](https://mlsanity.com/paper/2107.06239/) (2021)
- [IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiation](https://mlsanity.com/paper/2302.01058/) (2023)
- [ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning](https://mlsanity.com/paper/2307.01200/) (2023)
- [CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation](https://mlsanity.com/paper/2407.01244/) (2024)
- [ClothHMR: 3D Mesh Recovery of Humans in Diverse Clothing from Single Image](https://mlsanity.com/paper/2512.17545/) (2025)

## Abstract (arXiv)

The goal of many computer vision systems is to transform image pixels into 3D representations. Recent popular models use neural networks to regress directly from pixels to 3D object parameters. Such an approach works well when supervision is available, but in problems like human pose and shape estimation, it is difficult to obtain natural images with 3D ground truth. To go one step further, we propose a new architecture that facilitates unsupervised, or lightly supervised, learning. The idea is to break the problem into a series of transformations between increasingly abstract representations. Each step involves a cycle designed to be learnable without annotated training data, and the chain of cycles delivers the final solution. Specifically, we use 2D body part segments as an intermediate representation that contains enough information to be lifted to 3D, and at the same time is simple enough to be learned in an unsupervised way. We demonstrate the method by learning 3D human pose and shape from un-paired and un-annotated images. We also explore varying amounts of paired data and show that cycling greatly alleviates the need for paired data. While we present results for modeling humans, our formulation is general and can be applied to other vision problems.