mlsanityData to 7 Oct 2026

HyperNST: Hyper-Networks for Neural Style Transfer

arXiv 2208.04807 ↗First posted 9 Aug 2022cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

We present HyperNST; a neural style transfer (NST) technique for the artistic stylization of images, based on Hyper-networks and the StyleGAN2 architecture. Our contribution is a novel method for inducing style transfer parameterized by a metric space, pre-trained for style-based visual search (SBVS). We show for the first time that such space may be used to drive NST, enabling the application and interpolation of styles from an SBVS system. The technical contribution is a hyper-network that predicts weight updates to a StyleGAN2 pre-trained over a diverse gamut of artistic content (portraits), tailoring the style parameterization on a per-region basis using a semantic map of the facial regions. We show HyperNST to exceed state of the art in content preservation for our stylized content while retaining good style transfer performance.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 23 of its 27 references that are in the map. First posted on arXiv 9 Aug 2022.

Builds on

23 of 27 references.

References · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  6. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  7. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  8. 2016HyperNetworkscited by 1,003
  9. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  10. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  11. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  12. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
11 more
  1. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  2. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  3. 2021HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editingcited by 208
  4. 2018Arbitrary Style Transfer with Style-Attentional Networkscited by 197
  5. 2021General Facial Representation Learning in a Visual-Linguistic Mannercited by 193
  6. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  7. 2021BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generationcited by 47
  8. 2021ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similaritycited by 34
  9. 2022Neural Neighbor Style Transfercited by 23
  10. 2022Consistent Style Transfercited by 13
  11. 2022StyleBabel: Artistic Style Tagging and Captioningcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 0; 2025: 0; 2026: 1.

7 papers.

  1. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  2. 2023Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimationcited by 11
  3. 2023DIFF-NST: Diffusion Interleaving For deFormable Neural Style Transfercited by 5
  4. 2023NeAT: Neural Artistic Tracing for Beautiful Style Transfercited by 4
  5. 2023ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfercited by 3
  6. 2023Multi-Modal Face Stylization with a Generative Priorcited by 1
  7. 2026Neural Texture Compression using Hypernetworkscited by 0