# Unsupervised Training for 3D Morphable Model Regression

arXiv: https://arxiv.org/abs/1806.06098 · HTML: https://mlsanity.com/paper/1806.06098/

## Key facts

- Cited by 100 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2018.

## Built on by (most cited first, 30 of 100)

- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [EMOCA: Emotion Driven Monocular Face Capture and Animation](https://mlsanity.com/paper/2204.11312/) (2022)
- [Towards Metrical Reconstruction of Human Faces](https://mlsanity.com/paper/2204.06607/) (2022)
- [Collaborative Regression of Expressive Bodies using Moderation](https://mlsanity.com/paper/2105.05301/) (2021)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Emotional Speech-Driven Animation with Content-Emotion Disentanglement](https://mlsanity.com/paper/2306.08990/) (2023)
- [CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models](https://mlsanity.com/paper/2503.10592/) (2025)
- [SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis](https://mlsanity.com/paper/2404.04104/) (2024)
- [Fully Explicit Dynamic Gaussian Splatting](https://mlsanity.com/paper/2410.15629/) (2024)
- [3D face reconstruction with dense landmarks](https://mlsanity.com/paper/2204.02776/) (2022)
- [DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models](https://mlsanity.com/paper/2211.12131/) (2022)
- [AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANs](https://mlsanity.com/paper/2112.05957/) (2021)
- [SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting](https://mlsanity.com/paper/2109.01068/) (2021)
- [Face Relighting with Geometrically Consistent Shadows](https://mlsanity.com/paper/2203.16681/) (2022)
- [A Hierarchical Representation Network for Accurate and Detailed Face Reconstruction from In-The-Wild Images](https://mlsanity.com/paper/2302.14434/) (2023)
- [When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models](https://mlsanity.com/paper/2405.10255/) (2024)
- [Towards High Fidelity Face Relighting with Realistic Shadows](https://mlsanity.com/paper/2104.00825/) (2021)
- [FitMe: Deep Photorealistic 3D Morphable Model Avatars](https://mlsanity.com/paper/2305.09641/) (2023)
- [3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation](https://mlsanity.com/paper/2312.00311/) (2023)
- [Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement](https://mlsanity.com/paper/2106.11423/) (2021)
- [FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction](https://mlsanity.com/paper/2111.01082/) (2021)
- [Geometry-aware Single-image Full-body Human Relighting](https://mlsanity.com/paper/2207.04750/) (2022)
- [Relightify: Relightable 3D Faces from a Single Image via Diffusion Models](https://mlsanity.com/paper/2305.06077/) (2023)
- [Instant Multi-View Head Capture through Learnable Registration](https://mlsanity.com/paper/2306.07437/) (2023)
- [Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction](https://mlsanity.com/paper/2105.07474/) (2021)
- [REALY: Rethinking the Evaluation of 3D Face Reconstruction](https://mlsanity.com/paper/2203.09729/) (2022)
- [NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Images](https://mlsanity.com/paper/2303.12012/) (2023)
- [Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation](https://mlsanity.com/paper/2205.03962/) (2022)
- [Riggable 3D Face Reconstruction via In-Network Optimization](https://mlsanity.com/paper/2104.03493/) (2021)
- [SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction](https://mlsanity.com/paper/2106.03021/) (2021)

## Abstract (arXiv)

We present a method for training a regression network from image pixels to 3D morphable model coordinates using only unlabeled photographs. The training loss is based on features from a facial recognition network, computed on-the-fly by rendering the predicted faces with a differentiable renderer. To make training from features feasible and avoid network fooling effects, we introduce three objectives: a batch distribution loss that encourages the output distribution to match the distribution of the morphable model, a loopback loss that ensures the network can correctly reinterpret its own output, and a multi-view identity loss that compares the features of the predicted 3D face and the input photograph from multiple viewing angles. We train a regression network using these objectives, a set of unlabeled photographs, and the morphable model itself, and demonstrate state-of-the-art results.