mlsanityData to 7 Oct 2026

Fake It Till You Make It: Face analysis in the wild using synthetic data alone

arXiv 2109.15102 ↗First posted 30 Sep 2021cs.CVcited by 200

Not on the map. Why?

Abstract (arXiv)

We demonstrate that it is possible to perform face-related computer vision in the wild using synthetic data alone. The community has long enjoyed the benefits of synthesizing training data with graphics, but the domain gap between real and synthetic data has remained a problem, especially for human faces. Researchers have tried to bridge this gap with data mixing, domain adaptation, and domain-adversarial training, but we show that it is possible to synthesize data with minimal domain gap, so that models trained on synthetic data generalize to real in-the-wild datasets. We describe how to combine a procedurally-generated parametric 3D face model with a comprehensive library of hand-crafted assets to render training images with unprecedented realism and diversity. We train machine learning systems for face-related tasks such as landmark localization and face parsing, showing that synthetic data can both match real data in accuracy as well as open up new approaches where manual labelling would be impossible.

Key facts. Cited by 200 papers in the map (data through 7 Oct 2026). Builds on 39 of its 81 references that are in the map. First posted on arXiv 30 Sep 2021.

Builds on

39 of 81 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  7. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  8. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  9. 2017Learning from Synthetic Humanscited by 358
  10. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  11. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  12. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
27 more
  1. 2017GANerated Hands for Real-time 3D Hand Tracking from Monocular RGBcited by 147
  2. 2018Face Alignment in Full Pose Range: A 3D Total Solutioncited by 147
  3. 2017Morphable Face Models - An Open Frameworkcited by 138
  4. 2018Look at Boundary: A Boundary-Aware Face Alignment Algorithmcited by 137
  5. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  6. 2019Adaptive Wing Loss for Robust Face Alignment via Heatmap Regressioncited by 127
  7. 2019FairFace: Face Attribute Dataset for Balanced Race, Gender, and Agecited by 87
  8. 2016Learning Detailed Face Reconstruction from a Single Imagecited by 71
  9. 2019Photorealistic Image Synthesis for Object Instance Detectioncited by 66
  10. 20163D Face Reconstruction by Learning from Synthetic Datacited by 64
  11. 2020CONFIG: Controllable Neural Face Image Generationcited by 61
  12. 2017Unrestricted Facial Geometry Reconstruction Using Image-to-Image Translationcited by 56
  13. 2015Rendering of Eyes for Eye-Shape Registration and Gaze Estimationcited by 49
  14. 2018Domain Adaptation through Synthesis for Unsupervised Person Re-identificationcited by 44
  15. 2018Effective Use of Synthetic Data for Urban Scene Semantic Segmentationcited by 41
  16. 2019Simulating Content Consistent Vehicle Datasets with Attribute Descentcited by 35
  17. 2019Face Parsing with RoI Tanh-Warpingcited by 33
  18. 20193FabRec: Fast Few-shot Face alignment by Reconstructioncited by 33
  19. 2018DenseReg: Fully Convolutional Dense Shape Regression In-the-Wildcited by 32
  20. 2018Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Modelcited by 28
  21. 2019OpenEDS: Open Eye Datasetcited by 27
  22. 2020Edge-aware Graph Representation Learning and Reasoning for Face Parsingcited by 26
  23. 2014On Rendering Synthetic Images for Training an Object Detectorcited by 18
  24. 2019Laplace Landmark Localizationcited by 16
  25. 2020Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wildcited by 15
  26. 2017Hand2Face: Automatic Synthesis and Recognition of Hand Over Face Occlusionscited by 8
  27. 2020High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Imagescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 40; 2023: 50; 2024: 53; 2025: 37; 2026: 15.

200 papers.

Sort:

By area:

  1. 2024A Survey on Large Language Models for Code Generationcited by 646
  2. 2022Kubric: A scalable dataset generatorcited by 373
  3. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  4. 2023What does CLIP know about a red circle? Visual prompt engineering for VLMscited by 215
  5. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 142
  6. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
  7. 2024CinePile: A Long Video Question Answering Dataset and Benchmarkcited by 112
  8. 2024Best Practices and Lessons Learned on Synthetic Datacited by 104
  9. 2022DigiFace-1M: 1 Million Digital Face Images for Face Recognitioncited by 92
  10. 2024BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolationcited by 81
  11. 2023IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Modelscited by 72
  12. 20223D face reconstruction with dense landmarkscited by 70
38 more
  1. 2022MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptationcited by 69
  2. 2022Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptationcited by 67
  3. 2023Real-Time Radiance Fields for Single-Image Portrait View Synthesiscited by 64
  4. 2023Portrait4D: Learning One-Shot 4D Head Avatar Synthesis using Synthetic Datacited by 55
  5. 20244D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotationscited by 51
  6. 2022On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligencecited by 50
  7. 2022SimPer: Simple Self-Supervised Learning of Periodic Targetscited by 44
  8. 2024GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modelingcited by 44
  9. 2023GAIA: Zero-shot Talking Avatar Generationcited by 43
  10. 2023HandRefiner: Refining Malformed Hands in Generated Images by Diffusion-based Conditional Inpaintingcited by 42
  11. 2023STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detectioncited by 41
  12. 20233D Face Reconstruction with the Geometric Guidance of Facial Part Segmentationcited by 38
  13. 2022VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relightingcited by 37
  14. 2023AvatarBooth: High-Quality and Customizable 3D Human Avatar Generationcited by 37
  15. 2022VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representationscited by 36
  16. 2024RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Modelscited by 36
  17. 2023ArtiFact: A Large-Scale Dataset with Artificial and Factual Images for Generalizable and Robust Synthetic Image Detectioncited by 35
  18. 2024LRM-Zero: Training Large Reconstruction Models with Synthesized Datacited by 35
  19. 2022RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesiscited by 33
  20. 2022DAD-3DHeads: A Large-scale Dense, Accurate and Diverse Dataset for 3D Head Alignment from a Single Imagecited by 31
  21. 2022SCAMPS: Synthetics for Camera Measurement of Physiological Signalscited by 28
  22. 2022Synthetic Data in Human Analysis: A Surveycited by 28
  23. 2024EgoGen: An Egocentric Synthetic Data Generatorcited by 27
  24. 2024Position: Measure Dataset Diversity, Don't Just Claim Itcited by 26
  25. 2023StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generationcited by 25
  26. 20223D Segmentation of Humans in Point Clouds with Synthetic Datacited by 24
  27. 2025SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Facescited by 24
  28. 2022Shape Preserving Facial Landmarks with Graph Attention Networkscited by 23
  29. 2022Memories are One-to-Many Mapping Alleviators in Talking Face Generationcited by 22
  30. 2023HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Detailscited by 22
  31. 2024FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Headscited by 22
  32. 2024Real Risks of Fake Data: Synthetic Data, Diversity-Washing and Consent Circumventioncited by 21
  33. 2025BEDLAM2.0: Synthetic Humans and Cameras in Motioncited by 21
  34. 2025Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstructioncited by 20
  35. 2023Deep Learning Technique for Human Parsing: A Survey and Outlookcited by 18
  36. 2024ID3: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognitioncited by 18
  37. 2021Learning to Fit Morphable Modelscited by 16
  38. 2022PSP-HDRI+: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Modelscited by 15

50 most cited of 200 All 200 (JSON)