# TetraTSDF: 3D human reconstruction from a single image with a tetrahedral outer shell

arXiv: https://arxiv.org/abs/2004.10534 · HTML: https://mlsanity.com/paper/2004.10534/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2020.

## Built on by (most cited first, 18 of 18)

- [MeshDiffusion: Score-based Generative 3D Mesh Modeling](https://mlsanity.com/paper/2303.08133/) (2023)
- [SMPLicit: Topology-aware Generative Model for Clothed People](https://mlsanity.com/paper/2103.06871/) (2021)
- [TeCH: Text-guided Reconstruction of Lifelike Clothed Humans](https://mlsanity.com/paper/2308.08545/) (2023)
- [Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On](https://mlsanity.com/paper/2105.06462/) (2021)
- [CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition](https://mlsanity.com/paper/2304.03167/) (2023)
- [Structured 3D Features for Reconstructing Controllable Avatars](https://mlsanity.com/paper/2212.06820/) (2022)
- [Instant 3D Human Avatar Generation using Image Diffusion Models](https://mlsanity.com/paper/2406.07516/) (2024)
- [Data-Driven 3D Reconstruction of Dressed Humans From Sparse Views](https://mlsanity.com/paper/2104.08013/) (2021)
- [Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images](https://mlsanity.com/paper/2111.01884/) (2021)
- [Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Video](https://mlsanity.com/paper/2104.09259/) (2021)
- [Generalizing Adversarial Examples by AdaBelief Optimizer](https://mlsanity.com/paper/2101.09930/) (2021)
- [IWA: Integrated Gradient based White-box Attacks for Fooling Deep Neural Networks](https://mlsanity.com/paper/2102.02128/) (2021)
- [3D Reconstruction of Sculptures from Single Images via Unsupervised Domain Adaptation on Implicit Models](https://mlsanity.com/paper/2210.04265/) (2022)
- [An Embeddable Implicit IUVD Representation for Part-based 3D Human Surface Reconstruction](https://mlsanity.com/paper/2401.16810/) (2024)
- [Monocular Human Digitization via Implicit Re-projection Networks](https://mlsanity.com/paper/2205.06468/) (2022)
- [Weakly-Supervised 3D Reconstruction of Clothed Humans via Normal Maps](https://mlsanity.com/paper/2311.16042/) (2023)
- [Single-view 3D Body and Cloth Reconstruction under Complex Poses](https://mlsanity.com/paper/2205.04087/) (2022)
- [3D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review](https://mlsanity.com/paper/2509.12197/) (2025)

## Abstract (arXiv)

Recovering the 3D shape of a person from its 2D appearance is ill-posed due to ambiguities. Nevertheless, with the help of convolutional neural networks (CNN) and prior knowledge on the 3D human body, it is possible to overcome such ambiguities to recover detailed 3D shapes of human bodies from single images. Current solutions, however, fail to reconstruct all the details of a person wearing loose clothes. This is because of either (a) huge memory requirement that cannot be maintained even on modern GPUs or (b) the compact 3D representation that cannot encode all the details. In this paper, we propose the tetrahedral outer shell volumetric truncated signed distance function (TetraTSDF) model for the human body, and its corresponding part connection network (PCN) for 3D human body shape regression. Our proposed model is compact, dense, accurate, and yet well suited for CNN-based regression task. Our proposed PCN allows us to learn the distribution of the TSDF in the tetrahedral volume from a single image in an end-to-end manner. Results show that our proposed method allows to reconstruct detailed shapes of humans wearing loose clothes from single RGB images.