# 3D Facial Imperfection Regeneration: Deep learning approach and 3D printing prototypes

arXiv: https://arxiv.org/abs/2303.14381 · HTML: https://mlsanity.com/paper/2303.14381/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 73 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## Builds on (most cited first, 9 of 9)

- [Towards Metrical Reconstruction of Human Faces](https://mlsanity.com/paper/2204.06607/) (2022)
- [Partial FC: Training 10 Million Identities on a Single Machine](https://mlsanity.com/paper/2010.05222/) (2020)
- [Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression](https://mlsanity.com/paper/1703.07834/) (2017)
- [3D Face Reconstruction by Learning from Synthetic Data](https://mlsanity.com/paper/1609.04387/) (2016)
- [Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds](https://mlsanity.com/paper/1806.01759/) (2018)
- [Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels](https://mlsanity.com/paper/2006.04325/) (2020)
- [End-to-end 3D face reconstruction with deep neural networks](https://mlsanity.com/paper/1704.05020/) (2017)
- [MobileFace: 3D Face Reconstruction with Efficient CNN Regression](https://mlsanity.com/paper/1809.08809/) (2018)
- [Robust Bayesian Method for Simultaneous Block Sparse Signal Recovery with Applications to Face Recognition](https://mlsanity.com/paper/1605.02057/) (2016)

## Built on by (most cited first, 2 of 2)

- [Application of Self-Supervised Learning to MICA Model for Reconstructing Imperfect 3D Facial Structures](https://mlsanity.com/paper/2304.04060/) (2023)
- [Advancing Wound Filling Extraction on 3D Faces: Auto-Segmentation and Wound Face Regeneration Approach](https://mlsanity.com/paper/2307.01844/) (2023)

## Abstract (arXiv)

This study explores the potential of a fully convolutional mesh autoencoder model for regenerating 3D nature faces with the presence of imperfect areas. We utilize deep learning approaches in graph processing and analysis to investigate the capabilities model in recreating a filling part for facial scars. Our approach in dataset creation is able to generate a facial scar rationally in a virtual space that corresponds to the unique circumstances. Especially, we propose a new method which is named 3D Facial Imperfection Regeneration(3D-FaIR) for reproducing a complete face reconstruction based on the remaining features of the patient face. To further enhance the applicable capacity of the present research, we develop an improved outlier technique to separate the wounds of patients and provide appropriate wound cover models. Also, a Cir3D-FaIR dataset of imperfect faces and open codes was released at https://github.com/SIMOGroup/3DFaIR. Our findings demonstrate the potential of the proposed approach to help patients recover more quickly and safely through convenient techniques. We hope that this research can contribute to the development of new products and innovative solutions for facial scar regeneration.