# Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation

arXiv: https://arxiv.org/abs/2012.06178 · HTML: https://mlsanity.com/paper/2012.06178/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2020.

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

- [Super-resolution 3D Human Shape from a Single Low-Resolution Image](https://mlsanity.com/paper/2208.10738/) (2022)
- [VTP: Volumetric Transformer for Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2205.12602/) (2022)
- [Multi-view Human Body Mesh Translator](https://mlsanity.com/paper/2210.01886/) (2022)
- [COSMU: Complete 3D human shape from monocular unconstrained images](https://mlsanity.com/paper/2407.10586/) (2024)
- [3D Hand Mesh Recovery from Monocular RGB in Camera Space](https://mlsanity.com/paper/2405.07167/) (2024)
- [Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction](https://mlsanity.com/paper/2607.13646/) (2026)

## Abstract (arXiv)

The task of reconstructing detailed 3D human body models from images is interesting but challenging in computer vision due to the high freedom of human bodies. In order to tackle the problem, we propose a coarse-to-fine method to reconstruct a detailed 3D human body from multi-view images combining voxel super-resolution based on learning the implicit representation. Firstly, the coarse 3D models are estimated by learning an implicit representation based on multi-scale features which are extracted by multi-stage hourglass networks from the multi-view images. Then, taking the low resolution voxel grids which are generated by the coarse 3D models as input, the voxel super-resolution based on an implicit representation is learned through a multi-stage 3D convolutional neural network. Finally, the refined detailed 3D human body models can be produced by the voxel super-resolution which can preserve the details and reduce the false reconstruction of the coarse 3D models. Benefiting from the implicit representation, the training process in our method is memory efficient and the detailed 3D human body produced by our method from multi-view images is the continuous decision boundary with high-resolution geometry. In addition, the coarse-to-fine method based on voxel super-resolution can remove false reconstructions and preserve the appearance details in the final reconstruction, simultaneously. In the experiments, our method quantitatively and qualitatively achieves the competitive 3D human body reconstructions from images with various poses and shapes on both the real and synthetic datasets.