# MVF-Net: Multi-View 3D Face Morphable Model Regression

arXiv: https://arxiv.org/abs/1904.04473 · HTML: https://mlsanity.com/paper/1904.04473/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Apr 2019.

## Built on by (most cited first, 30 of 45)

- [H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction](https://mlsanity.com/paper/2107.12512/) (2021)
- [A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images](https://mlsanity.com/paper/2302.14434/) (2023)
- [Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement](https://mlsanity.com/paper/2106.11423/) (2021)
- [Instant Multi-View Head Capture through Learnable Registration](https://mlsanity.com/paper/2306.07437/) (2023)
- [REALY: Rethinking the Evaluation of 3D Face Reconstruction](https://mlsanity.com/paper/2203.09729/) (2022)
- [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)
- [Facial Geometric Detail Recovery via Implicit Representation](https://mlsanity.com/paper/2203.09692/) (2022)
- [DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis](https://mlsanity.com/paper/2312.13016/) (2023)
- [Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection](https://mlsanity.com/paper/2106.07852/) (2021)
- [Single-Shot Implicit Morphable Faces with Consistent Texture Parameterization](https://mlsanity.com/paper/2305.03043/) (2023)
- [Prior-Guided Multi-View 3D Head Reconstruction](https://mlsanity.com/paper/2107.04277/) (2021)
- [SIRA: Relightable Avatars from a Single Image](https://mlsanity.com/paper/2209.03027/) (2022)
- [DiffPortrait360: Consistent Portrait Diffusion for 360 View Synthesis](https://mlsanity.com/paper/2503.15667/) (2025)
- [Facial Depth and Normal Estimation using Single Dual-Pixel Camera](https://mlsanity.com/paper/2111.12928/) (2021)
- [Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstruction](https://mlsanity.com/paper/2310.08784/) (2023)
- [Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture](https://mlsanity.com/paper/2406.00440/) (2024)
- [Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglement](https://mlsanity.com/paper/2102.10544/) (2021)
- [SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surface](https://mlsanity.com/paper/2403.18784/) (2024)
- [Neuromorphic Facial Analysis with Cross-Modal Supervision](https://mlsanity.com/paper/2409.10213/) (2024)
- [ASM: Adaptive Skinning Model for High-Quality 3D Face Modeling](https://mlsanity.com/paper/2304.09423/) (2023)
- [High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering](https://mlsanity.com/paper/2401.08398/) (2024)
- [Implicit Neural Deformation for Sparse-View Face Reconstruction](https://mlsanity.com/paper/2112.02494/) (2021)
- [InstantAvatar: Efficient 3D Head Reconstruction via Surface Rendering](https://mlsanity.com/paper/2308.04868/) (2023)
- [VGGTFace: Topologically Consistent Facial Geometry Reconstruction in the Wild](https://mlsanity.com/paper/2511.20366/) (2025)
- [FLAME-based Multi-View 3D Face Reconstruction](https://mlsanity.com/paper/2308.07551/) (2023)
- [Disjoint Pose and Shape for 3D Face Reconstruction](https://mlsanity.com/paper/2308.13903/) (2023)
- [High-Quality 3D Face Reconstruction with Affine Convolutional Networks](https://mlsanity.com/paper/2310.14237/) (2023)
- [PIFu for the Real World: A Self-supervised Framework to Reconstruct Dressed Human from Single-view Images](https://mlsanity.com/paper/2208.10769/) (2022)
- [Spatio-temporal Transformers for Action Unit Classification with Event Cameras](https://mlsanity.com/paper/2410.21958/) (2024)

## Abstract (arXiv)

We address the problem of recovering the 3D geometry of a human face from a set of facial images in multiple views. While recent studies have shown impressive progress in 3D Morphable Model (3DMM) based facial reconstruction, the settings are mostly restricted to a single view. There is an inherent drawback in the single-view setting: the lack of reliable 3D constraints can cause unresolvable ambiguities. We in this paper explore 3DMM-based shape recovery in a different setting, where a set of multi-view facial images are given as input. A novel approach is proposed to regress 3DMM parameters from multi-view inputs with an end-to-end trainable Convolutional Neural Network (CNN). Multiview geometric constraints are incorporated into the network by establishing dense correspondences between different views leveraging a novel self-supervised view alignment loss. The main ingredient of the view alignment loss is a differentiable dense optical flow estimator that can backpropagate the alignment errors between an input view and a synthetic rendering from another input view, which is projected to the target view through the 3D shape to be inferred. Through minimizing the view alignment loss, better 3D shapes can be recovered such that the synthetic projections from one view to another can better align with the observed image. Extensive experiments demonstrate the superiority of the proposed method over other 3DMM methods.