# DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment

arXiv: https://arxiv.org/abs/2305.11522 · HTML: https://mlsanity.com/paper/2305.11522/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 56 references that are in the map.
- First posted on arXiv 19 May 2023.

## Builds on (most cited first, 30 of 37)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set](https://mlsanity.com/paper/1903.08527/) (2019)
- [Learning an Animatable Detailed 3D Face Model from In-The-Wild Images](https://mlsanity.com/paper/2012.04012/) (2020)
- [Towards Fast, Accurate and Stable 3D Dense Face Alignment](https://mlsanity.com/paper/2009.09960/) (2020)
- [Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network](https://mlsanity.com/paper/1803.07835/) (2018)
- [Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision](https://mlsanity.com/paper/1905.06817/) (2019)
- [Towards Metrical Reconstruction of Human Faces](https://mlsanity.com/paper/2204.06607/) (2022)
- [Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network](https://mlsanity.com/paper/1612.04904/) (2016)
- [Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency](https://mlsanity.com/paper/2007.12494/) (2020)
- [3D face reconstruction with dense landmarks](https://mlsanity.com/paper/2204.02776/) (2022)
- [Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression](https://mlsanity.com/paper/1703.07834/) (2017)
- [6D Rotation Representation For Unconstrained Head Pose Estimation](https://mlsanity.com/paper/2202.12555/) (2022)
- [img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation](https://mlsanity.com/paper/2012.07791/) (2020)
- [Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translation](https://mlsanity.com/paper/1703.10131/) (2017)
- [On Learning 3D Face Morphable Model from In-the-wild Images](https://mlsanity.com/paper/1808.09560/) (2018)
- [WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose](https://mlsanity.com/paper/2005.10353/) (2020)
- [A Vector-based Representation to Enhance Head Pose Estimation](https://mlsanity.com/paper/2010.07184/) (2020)
- [DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild](https://mlsanity.com/paper/1803.02188/) (2018)
- [SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction](https://mlsanity.com/paper/2106.03021/) (2021)
- [Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry](https://mlsanity.com/paper/2110.09772/) (2021)
- [Dense Face Alignment](https://mlsanity.com/paper/1709.01442/) (2017)
- [Multi-task head pose estimation in-the-wild](https://mlsanity.com/paper/2202.02299/) (2022)
- [Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses](https://mlsanity.com/paper/1707.05653/) (2017)
- [Self-Supervised 3D Face Reconstruction via Conditional Estimation](https://mlsanity.com/paper/2110.04800/) (2021)
- [S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Image](https://mlsanity.com/paper/2203.07732/) (2022)

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

- [On the representation and methodology for wide and short range head pose estimation](https://mlsanity.com/paper/2401.05807/) (2024)
- [ImFace++: A Sophisticated Nonlinear 3D Morphable Face Model with Implicit Neural Representations](https://mlsanity.com/paper/2312.04028/) (2023)
- [Semi-Supervised Unconstrained Head Pose Estimation in the Wild](https://mlsanity.com/paper/2404.02544/) (2024)
- [3D Face Alignment Through Fusion of Head Pose Information and Features](https://mlsanity.com/paper/2308.13327/) (2023)
- [Robust 3D Face Alignment with Multi-Path Neural Architecture Search](https://mlsanity.com/paper/2406.07873/) (2024)
- [On the power of data augmentation for head pose estimation](https://mlsanity.com/paper/2407.05357/) (2024)

## Abstract (arXiv)

Sensitivity to severe occlusion and large view angles limits the usage scenarios of the existing monocular 3D dense face alignment methods. The state-of-the-art 3DMM-based method, directly regresses the model's coefficients, underutilizing the low-level 2D spatial and semantic information, which can actually offer cues for face shape and orientation. In this work, we demonstrate how modeling 3D facial geometry in image and model space jointly can solve the occlusion and view angle problems. Instead of predicting the whole face directly, we regress image space features in the visible facial region by dense prediction first. Subsequently, we predict our model's coefficients based on the regressed feature of the visible regions, leveraging the prior knowledge of whole face geometry from the morphable models to complete the invisible regions. We further propose a fusion network that combines the advantages of both the image and model space predictions to achieve high robustness and accuracy in unconstrained scenarios. Thanks to the proposed fusion module, our method is robust not only to occlusion and large pitch and roll view angles, which is the benefit of our image space approach, but also to noise and large yaw angles, which is the benefit of our model space method. Comprehensive evaluations demonstrate the superior performance of our method compared with the state-of-the-art methods. On the 3D dense face alignment task, we achieve 3.80% NME on the AFLW2000-3D dataset, which outperforms the state-of-the-art method by 5.5%. Code is available at https://github.com/lhyfst/DSFNet.