# HumanMeshNet: Polygonal Mesh Recovery of Humans

arXiv: https://arxiv.org/abs/1908.06544 · HTML: https://mlsanity.com/paper/1908.06544/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [SHARP: Shape-Aware Reconstruction of People in Loose Clothing](https://mlsanity.com/paper/2205.11948/) (2022)
- [What's the Situation with Intelligent Mesh Generation: A Survey and Perspectives](https://mlsanity.com/paper/2211.06009/) (2022)
- [Instance-Level Task Parameters: A Robust Multi-task Weighting Framework](https://mlsanity.com/paper/2106.06129/) (2021)
- [DC-GNet: Deep Mesh Relation Capturing Graph Convolution Network for 3D Human Shape Reconstruction](https://mlsanity.com/paper/2108.12384/) (2021)
- [Reconstruction of People in Loose Clothing](https://mlsanity.com/paper/2106.04778/) (2021)
- [Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art](https://mlsanity.com/paper/2311.10129/) (2023)

## Abstract (arXiv)

3D Human Body Reconstruction from a monocular image is an important problem in computer vision with applications in virtual and augmented reality platforms, animation industry, en-commerce domain, etc. While several of the existing works formulate it as a volumetric or parametric learning with complex and indirect reliance on re-projections of the mesh, we would like to focus on implicitly learning the mesh representation. To that end, we propose a novel model, HumanMeshNet, that regresses a template mesh's vertices, as well as receives a regularization by the 3D skeletal locations in a multi-branch, multi-task setup. The image to mesh vertex regression is further regularized by the neighborhood constraint imposed by mesh topology ensuring smooth surface reconstruction. The proposed paradigm can theoretically learn local surface deformations induced by body shape variations and can therefore learn high-resolution meshes going ahead. We show comparable performance with SoA (in terms of surface and joint error) with far lesser computational complexity, modeling cost and therefore real-time reconstructions on three publicly available datasets. We also show the generalizability of the proposed paradigm for a similar task of predicting hand mesh models. Given these initial results, we would like to exploit the mesh topology in an explicit manner going ahead.