mlsanityData to 7 Oct 2026

Diverse Image-to-Image Translation via Disentangled Representations

arXiv 1808.00948 ↗First posted 2 Aug 2018cs.CVcited by 296

Not on the map. Why?

Cited by 20 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image-to-image translation aims to learn the mapping between two visual domains. There are two main challenges for many applications: 1) the lack of aligned training pairs and 2) multiple possible outputs from a single input image. In this work, we present an approach based on disentangled representation for producing diverse outputs without paired training images. To achieve diversity, we propose to embed images onto two spaces: a domain-invariant content space capturing shared information across domains and a domain-specific attribute space. Our model takes the encoded content features extracted from a given input and the attribute vectors sampled from the attribute space to produce diverse outputs at test time. To handle unpaired training data, we introduce a novel cross-cycle consistency loss based on disentangled representations. Qualitative results show that our model can generate diverse and realistic images on a wide range of tasks without paired training data. For quantitative comparisons, we measure realism with user study and diversity with a perceptual distance metric. We apply the proposed model to domain adaptation and show competitive performance when compared to the state-of-the-art on the MNIST-M and the LineMod datasets.

Key facts. Cited by 296 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 83; 2022: 58; 2023: 68; 2024: 33; 2025: 29; 2026: 23.

296 papers.

Sort:

By area:

  1. 2023Zero-shot Image-to-Image Translationcited by 503
  2. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  3. 2021GAN Inversion: A Surveycited by 366
  4. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
  5. 2021Audio-Driven Emotional Video Portraitscited by 180
  6. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
  7. 2023Multi-modal Learning with Missing Modality via Shared-Specific Feature Modellingcited by 159
  8. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Modelscited by 154
  9. 2021UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Modelscited by 133
  10. 2022Semantic Image Synthesis via Diffusion Modelscited by 131
  11. 2021Hallucinated Neural Radiance Fields in the Wildcited by 130
  12. 2021Learning Debiased Representation via Disentangled Feature Augmentationcited by 116
38 more
  1. 2022Disentangled Representation Learningcited by 111
  2. 2024One-Step Image Translation with Text-to-Image Modelscited by 111
  3. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  4. 2023DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generationcited by 75
  5. 2021Enhancing Photorealism Enhancementcited by 74
  6. 2021Dual Contrastive Learning for Unsupervised Image-to-Image Translationcited by 65
  7. 2022DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformerscited by 65
  8. 2021High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Networkcited by 61
  9. 2021In&Out : Diverse Image Outpainting via GAN Inversioncited by 55
  10. 2022Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignmentcited by 54
  11. 2021Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Datacited by 53
  12. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  13. 2022STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Datasetcited by 52
  14. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  15. 2021Vector-Decomposed Disentanglement for Domain-Invariant Object Detectioncited by 47
  16. 2021BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generationcited by 47
  17. 2022A survey of multimodal deep generative modelscited by 47
  18. 2021Style Normalization and Restitution for Domain Generalization and Adaptationcited by 46
  19. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  20. 2022CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfercited by 46
  21. 2021Vision Transformers with Patch Diversificationcited by 45
  22. 2021Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translationcited by 45
  23. 2021Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGANcited by 45
  24. 2022UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translationcited by 42
  25. 2022Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Modelcited by 39
  26. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
  27. 2021Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspectivecited by 37
  28. 2023Exploiting Diffusion Prior for Generalizable Dense Predictioncited by 37
  29. 2021Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translationcited by 35
  30. 2022Do better ImageNet classifiers assess perceptual similarity better?cited by 34
  31. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  32. 2023DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Modelscited by 33
  33. 2021Self-Adversarial Disentangling for Specific Domain Adaptationcited by 29
  34. 2021StyleFusion: A Generative Model for Disentangling Spatial Segmentscited by 28
  35. 2023Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentationcited by 28
  36. 2023MaLP: Manipulation Localization Using a Proactive Schemecited by 26
  37. 2021Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesiscited by 24
  38. 2021Conditional Invertible Neural Networks for Diverse Image-to-Image Translationcited by 24

50 most cited of 296 All 296 (JSON)