# Towards Robust RGB-D Human Mesh Recovery

arXiv: https://arxiv.org/abs/1911.07383 · HTML: https://mlsanity.com/paper/1911.07383/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2019.

## Built on by (most cited first, 3 of 3)

- [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)
- [Heuristic Weakly Supervised 3D Human Pose Estimation](https://mlsanity.com/paper/2105.10996/) (2021)

## Abstract (arXiv)

We consider the problem of human pose estimation. While much recent work has focused on the RGB domain, these techniques are inherently under-constrained since there can be many 3D configurations that explain the same 2D projection. To this end, we propose a new method that uses RGB-D data to estimate a parametric human mesh model. Our key innovations include (a) the design of a new dynamic data fusion module that facilitates learning with a combination of RGB-only and RGB-D datasets, (b) a new constraint generator module that provides SMPL supervisory signals when explicit SMPL annotations are not available, and (c) the design of a new depth ranking learning objective, all of which enable principled model training with RGB-D data. We conduct extensive experiments on a variety of RGB-D datasets to demonstrate efficacy.