# Topologically Consistent Multi-View Face Inference Using Volumetric Sampling

arXiv: https://arxiv.org/abs/2110.02948 · HTML: https://mlsanity.com/paper/2110.02948/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 66 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [Generating 3D faces using Convolutional Mesh Autoencoders](https://mlsanity.com/paper/1807.10267/) (2018)
- [Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision](https://mlsanity.com/paper/1905.06817/) (2019)
- [Neural Volumes: Learning Dynamic Renderable Volumes from Images](https://mlsanity.com/paper/1906.07751/) (2019)
- [MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction](https://mlsanity.com/paper/1703.10580/) (2017)
- [Learnable Triangulation of Human Pose](https://mlsanity.com/paper/1905.05754/) (2019)
- [Unsupervised Training for 3D Morphable Model Regression](https://mlsanity.com/paper/1806.06098/) (2018)
- [Learning Formation of Physically-Based Face Attributes](https://mlsanity.com/paper/2004.03458/) (2020)
- [Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz](https://mlsanity.com/paper/1712.02859/) (2017)
- [Towards High-fidelity Nonlinear 3D Face Morphable Model](https://mlsanity.com/paper/1904.04933/) (2019)
- [FML: Face Model Learning from Videos](https://mlsanity.com/paper/1812.07603/) (2018)
- [3D Face Reconstruction by Learning from Synthetic Data](https://mlsanity.com/paper/1609.04387/) (2016)
- [MVF-Net: Multi-View 3D Face Morphable Model Regression](https://mlsanity.com/paper/1904.04473/) (2019)
- [ExpNet: Landmark-Free, Deep, 3D Facial Expressions](https://mlsanity.com/paper/1802.00542/) (2018)
- [Dynamic Facial Asset and Rig Generation from a Single Scan](https://mlsanity.com/paper/2010.00560/) (2020)
- [Fitting a 3D Morphable Model to Edges: A Comparison Between Hard and Soft Correspondences](https://mlsanity.com/paper/1602.01125/) (2016)
- [Extreme 3D Face Reconstruction: Seeing Through Occlusions](https://mlsanity.com/paper/1712.05083/) (2017)

## Abstract (arXiv)

High-fidelity face digitization solutions often combine multi-view stereo (MVS) techniques for 3D reconstruction and a non-rigid registration step to establish dense correspondence across identities and expressions. A common problem is the need for manual clean-up after the MVS step, as 3D scans are typically affected by noise and outliers and contain hairy surface regions that need to be cleaned up by artists. Furthermore, mesh registration tends to fail for extreme facial expressions. Most learning-based methods use an underlying 3D morphable model (3DMM) to ensure robustness, but this limits the output accuracy for extreme facial expressions. In addition, the global bottleneck of regression architectures cannot produce meshes that tightly fit the ground truth surfaces. We propose ToFu, Topologically consistent Face from multi-view, a geometry inference framework that can produce topologically consistent meshes across facial identities and expressions using a volumetric representation instead of an explicit underlying 3DMM. Our novel progressive mesh generation network embeds the topological structure of the face in a feature volume, sampled from geometry-aware local features. A coarse-to-fine architecture facilitates dense and accurate facial mesh predictions in a consistent mesh topology. ToFu further captures displacement maps for pore-level geometric details and facilitates high-quality rendering in the form of albedo and specular reflectance maps. These high-quality assets are readily usable by production studios for avatar creation, animation and physically-based skin rendering. We demonstrate state-of-the-art geometric and correspondence accuracy, while only taking 0.385 seconds to compute a mesh with 10K vertices, which is three orders of magnitude faster than traditional techniques. The code and the model are available for research purposes at https://tianyeli.github.io/tofu.