mlsanityData to 7 Oct 2026

Hypercomplex Image-to-Image Translation

arXiv 2205.02087 ↗First posted 4 May 2022cs.CV cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Image-to-image translation (I2I) aims at transferring the content representation from an input domain to an output one, bouncing along different target domains. Recent I2I generative models, which gain outstanding results in this task, comprise a set of diverse deep networks each with tens of million parameters. Moreover, images are usually three-dimensional being composed of RGB channels and common neural models do not take dimensions correlation into account, losing beneficial information. In this paper, we propose to leverage hypercomplex algebra properties to define lightweight I2I generative models capable of preserving pre-existing relations among image dimensions, thus exploiting additional input information. On manifold I2I benchmarks, we show how the proposed Quaternion StarGANv2 and parameterized hypercomplex StarGANv2 (PHStarGANv2) reduce parameters and storage memory amount while ensuring high domain translation performance and good image quality as measured by FID and LPIPS scores. Full code is available at: https://github.com/ispamm/HI2I.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 37 of its 46 references that are in the map. First posted on arXiv 4 May 2022.

Builds on

37 of 46 references.

References · 37

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  5. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  6. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  7. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  8. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  9. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  10. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  11. 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 458
  12. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
25 more
  1. 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 260
  2. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  3. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  4. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  5. 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
  6. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  7. 2019Adaptive Wing Loss for Robust Face Alignment via Heatmap Regressioncited by 127
  8. 2020Cross-domain Correspondence Learning for Exemplar-based Image Translationcited by 116
  9. 2018Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Datacited by 76
  10. 2021Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with 1/n Parameterscited by 66
  11. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  12. 2018Quaternion Recurrent Neural Networkscited by 41
  13. 2020Distilling portable Generative Adversarial Networks for Image Translationcited by 36
  14. 2018Quaternion Convolutional Neural Networks for Heterogeneous Image Processingcited by 29
  15. 2021ZerO Initialization: Initializing Neural Networks with only Zeros and Onescited by 28
  16. 2021PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutionscited by 26
  17. 2018Quaternion Convolutional Neural Networks for Detection and Localization of 3D Sound Eventscited by 18
  18. 2021Quaternion Generative Adversarial Networkscited by 17
  19. 2019Exploring Explicit Domain Supervision for Latent Space Disentanglement in Unpaired Image-to-Image Translationcited by 13
  20. 2021GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation (works for videos too!)cited by 13
  21. 2020A Quaternion-Valued Variational Autoencodercited by 11
  22. 2020AlgebraNetscited by 7
  23. 2021Parameterized Hypercomplex Graph Neural Networks for Graph Classificationcited by 7
  24. 2020Hypercomplex-Valued Recurrent Correlation Neural Networkscited by 6
  25. 2019Compressing deep quaternion neural networks with targeted regularizationcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 4.

4 papers.

  1. 2023Generalizing Medical Image Representations via Quaternion Wavelet Networkscited by 6
  2. 2023StawGAN: Structural-Aware Generative Adversarial Networks for Infrared Image Translationcited by 4
  3. 2023Quaternion Convolutional Neural Networks: Current Advances and Future Directionscited by 3
  4. 2023PHYDI: Initializing Parameterized Hypercomplex Neural Networks as Identity Functionscited by 2