mlsanityData to 14 Oct 2026

Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation

arXiv 2110.05055 ↗First posted 11 Oct 2021cs.CV cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The image-to-image translation (I2IT) model takes a target label or a reference image as the input, and changes a source into the specified target domain. The two types of synthesis, either label- or reference-based, have substantial differences. Particularly, the label-based synthesis reflects the common characteristics of the target domain, and the reference-based shows the specific style similar to the reference. This paper intends to bridge the gap between them in the task of multi-attribute I2IT. We design the label- and reference-based encoding modules (LEM and REM) to compare the domain differences. They first transfer the source image and target label (or reference) into a common embedding space, by providing the opposite directions through the attribute difference vector. Then the two embeddings are simply fused together to form the latent code S_rand (or S_ref), reflecting the domain style differences, which is injected into each layer of the generator by SPADE. To link LEM and REM, so that two types of results benefit each other, we encourage the two latent codes to be close, and set up the cycle consistency between the forward and backward translations on them. Moreover, the interpolation between the S_rand and S_ref is also used to synthesize an extra image. Experiments show that label- and reference-based synthesis are indeed mutually promoted, so that we can have the diverse results from LEM, and high quality results with the similar style of the reference.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 11 Oct 2021.

Builds on

35 of 46 references.

References · 35

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2016Improved Techniques for Training GANscited by 2,970
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2014Conditional Generative Adversarial Netscited by 2,162
  7. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  8. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  9. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
  10. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  11. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  12. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
23 more
  1. 2017Unsupervised Image-to-Image Translation Networkscited by 603
  2. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  3. 2017Toward Multimodal Image-to-Image Translationcited by 296
  4. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  5. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  6. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 242
  7. 2019Few-Shot Unsupervised Image-to-Image Translationcited by 222
  8. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  9. 2018A Variational U-Net for Conditional Appearance and Shape Generationcited by 124
  10. 2019STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editingcited by 120
  11. 2019Diversity-Sensitive Conditional Generative Adversarial Networkscited by 77
  12. 2019RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributescited by 56
  13. 2020Rethinking the Truly Unsupervised Image-to-Image Translationcited by 56
  14. 2018ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributescited by 50
  15. 2017CVAE-GAN: Fine-Grained Image Generation through Asymmetric Trainingcited by 42
  16. 2019LOGAN: Latent Optimisation for Generative Adversarial Networkscited by 42
  17. 2019Multi-mapping Image-to-Image Translation via Learning Disentanglementcited by 35
  18. 2018SMIT: Stochastic Multi-Label Image-to-Image Translationcited by 21
  19. 2018Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensionscited by 19
  20. 2020GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modelingcited by 11
  21. 2020Gradient Origin Networkscited by 10
  22. 2020Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encodercited by 10
  23. 2019Disentangling the Spatial Structure and Style in Conditional VAEcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Style Transformer for Image Inversion and Editingcited by 37