mlsanityData to 14 Oct 2026

'Tax-free' 3DMM Conditional Face Generation

arXiv 2305.13460 ↗First posted 22 May 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

3DMM conditioned face generation has gained traction due to its well-defined controllability; however, the trade-off is lower sample quality: Previous works such as DiscoFaceGAN and 3D-FM GAN show a significant FID gap compared to the unconditional StyleGAN, suggesting that there is a quality tax to pay for controllability. In this paper, we challenge the assumption that quality and controllability cannot coexist. To pinpoint the previous issues, we mathematically formalize the problem of 3DMM conditioned face generation. Then, we devise simple solutions to the problem under our proposed framework. This results in a new model that effectively removes the quality tax between 3DMM conditioned face GANs and the unconditional StyleGAN.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 31 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

24 of 31 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  5. 2022A ConvNet for the 2020scited by 3,579
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  7. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  8. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  9. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  10. 2018Which Training Methods for GANs do actually Converge?cited by 679
  11. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  12. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
12 more
  1. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 482
  2. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 441
  3. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 349
  4. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 332
  5. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 268
  6. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 220
  7. 2019Fixup Initialization: Residual Learning Without Normalizationcited by 198
  8. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  9. 2020The Hessian Penalty: A Weak Prior for Unsupervised Disentanglementcited by 92
  10. 2020GIF: Generative Interpretable Facescited by 53
  11. 2020Semi-Supervised StyleGAN for Disentanglement Learningcited by 43
  12. 20223D-FM GAN: Towards 3D-Controllable Face Manipulationcited by 17

Built on by

Not cited yet.