mlsanityData to 7 Oct 2026

Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval

arXiv 2107.06256 ↗First posted 13 Jul 2021cs.CV cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

We present Retrieve in Style (RIS), an unsupervised framework for facial feature transfer and retrieval on real images. Recent work shows capabilities of transferring local facial features by capitalizing on the disentanglement property of the StyleGAN latent space. RIS improves existing art on the following: 1) Introducing more effective feature disentanglement to allow for challenging transfers (ie, hair, pose) that were not shown possible in SoTA methods. 2) Eliminating the need for per-image hyperparameter tuning, and for computing a catalog over a large batch of images. 3) Enabling fine-grained face retrieval using disentangled facial features (eg, eyes). To our best knowledge, this is the first work to retrieve face images at this fine level. 4) Demonstrating robust, natural editing on real images. Our qualitative and quantitative analyses show RIS achieves both high-fidelity feature transfers and accurate fine-grained retrievals on real images. We also discuss the responsible applications of RIS.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 13 Jul 2021.

Builds on

34 of 47 references.

References · 34

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  9. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  10. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  11. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  12. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
22 more
  1. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  2. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  3. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  4. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  5. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  6. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  7. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 267
  8. 2019On the "steerability" of generative adversarial networkscited by 247
  9. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  10. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  11. 2019Effectively Unbiased FID and Inception Score and where to find themcited by 161
  12. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  13. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  14. 2020Generative Hierarchical Features from Synthesizing Imagescited by 83
  15. 2018Towards Open-Set Identity Preserving Face Synthesiscited by 74
  16. 2019Mask-Guided Portrait Editing with Conditional GANscited by 61
  17. 2020CONFIG: Controllable Neural Face Image Generationcited by 61
  18. 2014Deeply learned face representations are sparse, selective, and robustcited by 56
  19. 2017Towards Large-Pose Face Frontalization in the Wildcited by 50
  20. 2018ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributescited by 50
  21. 2020Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Spacecited by 34
  22. 2018Spatially Controllable Image Synthesis with Internal Representation Collagingcited by 23

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 8; 2023: 3; 2024: 2.

15 papers.

Sort:

By area:

  1. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  2. 2022Fine-Grained Face Swapping via Regional GAN Inversioncited by 67
  3. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  4. 2021JoJoGAN: One Shot Face Stylizationcited by 49
  5. 2022PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANscited by 20
  6. 2022GAN-based Facial Attribute Manipulationcited by 16
  7. 2023E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversioncited by 8
  8. 2023ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirectioncited by 6
  9. 2022Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANscited by 4
  10. 2022Disentangling Random and Cyclic Effects in Time-Lapse Sequencescited by 3
  11. 2022Physically Disentangled Representationscited by 1
  12. 2024Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrievalcited by 1
3 more
  1. 2024Extrapolating Prospective Glaucoma Fundus Images through Diffusion Model in Irregular Longitudinal Sequencescited by 1
  2. 2022Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGANcited by 0
  3. 2023StyleDiff: Attribute Comparison Between Unlabeled Datasets in Latent Disentangled Spacecited by 0