mlsanityData to 7 Oct 2026

FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks

arXiv 2112.00532 ↗First posted 1 Dec 2021cs.CV cs.GRcited by 9

Not on the map. Why?

Abstract (arXiv)

In this paper, we present FaceTuneGAN, a new 3D face model representation decomposing and encoding separately facial identity and facial expression. We propose a first adaptation of image-to-image translation networks, that have successfully been used in the 2D domain, to 3D face geometry. Leveraging recently released large face scan databases, a neural network has been trained to decouple factors of variations with a better knowledge of the face, enabling facial expressions transfer and neutralization of expressive faces. Specifically, we design an adversarial architecture adapting the base architecture of FUNIT and using SpiralNet++ for our convolutional and sampling operations. Using two publicly available datasets (FaceScape and CoMA), FaceTuneGAN has a better identity decomposition and face neutralization than state-of-the-art techniques. It also outperforms classical deformation transfer approach by predicting blendshapes closer to ground-truth data and with less of undesired artifacts due to too different facial morphologies between source and target.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 38 of its 70 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

38 of 70 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  12. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
26 more
  1. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  2. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  3. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  4. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  5. 2018Which Training Methods for GANs do actually Converge?cited by 672
  6. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  7. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  8. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  9. 20193D Morphable Face Models -- Past, Present and Futurecited by 269
  10. 2018Generating 3D faces using Convolutional Mesh Autoencoderscited by 267
  11. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  12. 2019Understanding and Improving Layer Normalizationcited by 213
  13. 2020FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Predictioncited by 196
  14. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  15. 2016Unsupervised Cross-Domain Image Generationcited by 125
  16. 2020Learning Formation of Physically-Based Face Attributescited by 94
  17. 2016Learning Dense Correspondence via 3D-guided Cycle Consistencycited by 91
  18. 2019Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generationcited by 89
  19. 2019SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operatorcited by 89
  20. 2019Disentangled Representation Learning for 3D Face Shapecited by 48
  21. 2018A Simple Approach to Intrinsic Correspondence Learning on Unstructured 3D Meshescited by 39
  22. 20193DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translationcited by 27
  23. 2017Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoderscited by 11
  24. 2020A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Facescited by 11
  25. 20203DSNet: Unsupervised Shape-to-Shape 3D Style Transfercited by 9
  26. 2021Disentangled Face Identity Representations for joint 3D Face Recognition and Expression Neutralisationcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 2; 2025: 3.

9 papers.

  1. 2023Towards Realistic Generative 3D Face Modelscited by 20
  2. 2022Controllable 3D Generative Adversarial Face Model via Disentangling Shape and Appearancecited by 8
  3. 20233D Generative Model Latent Disentanglement via Local Eigenprojectioncited by 6
  4. 20243D Face Modeling via Weakly-supervised Disentanglement Network joint Identity-consistency Priorcited by 1
  5. 2025GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatarscited by 1
  6. 2023FISTNet: FusIon of STyle-path generative Networks for Facial Style Transfercited by 0
  7. 2024DrFER: Learning Disentangled Representations for 3D Facial Expression Recognitioncited by 0
  8. 2025Self-Attention Based Multi-Scale Graph Auto-Encoder Network of 3D Meshescited by 0
  9. 2025Multimodal Conditional MeshGAN for Personalized Aneurysm Growth Predictioncited by 0