mlsanityData to 7 Oct 2026

Improving Shape Deformation in Unsupervised Image-to-Image Translation

arXiv 1808.04325 ↗First posted 13 Aug 2018cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change. Inspired by semantic segmentation, we introduce a discriminator with dilated convolutions that is able to use information from across the entire image to train a more context-aware generator. This is coupled with a multi-scale perceptual loss that is better able to represent error in the underlying shape of objects. We demonstrate that this design is more capable of representing shape deformation in a challenging toy dataset, plus in complex mappings with significant dataset variation between humans, dolls, and anime faces, and between cats and dogs.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 4; 2023: 6; 2024: 0; 2025: 2.

19 papers.

Sort:

By area:

  1. 2022EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equationscited by 172
  2. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  3. 2021DG-Font: Deformable Generative Networks for Unsupervised Font Generationcited by 70
  4. 2023AGTGAN: Unpaired Image Translation for Photographic Ancient Character Generationcited by 17
  5. 2021Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusioncited by 11
  6. 2021USIS: Unsupervised Semantic Image Synthesiscited by 8
  7. 2021A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translationcited by 8
  8. 2022Collaborative Neural Rendering using Anime Character Sheetscited by 8
  9. 2023Leveraging generative adversarial networks to create realistic scanning transmission electron microscopy imagescited by 8
  10. 2023Unpaired Image-to-Image Translation with Limited Data to Reveal Subtle Phenotypescited by 7
  11. 2021DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesiscited by 3
  12. 2025FCR: Investigating Generative AI models for Forensic Craniofacial Reconstructioncited by 3
7 more
  1. 2022DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generationcited by 2
  2. 2022Experiments on Anomaly Detection in Autonomous Driving by Forward-Backward Style Transferscited by 1
  3. 2023Jurassic World Remake: Bringing Ancient Fossils Back to Life via Zero-Shot Long Image-to-Image Translationcited by 1
  4. 2023Human Machine Co-Creation. A Complementary Cognitive Approach to Creative Character Design Process Using GANscited by 1
  5. 2021Few-Shot Unsupervised Image-to-Image Translation on complex scenescited by 0
  6. 2023Exploring the Power of Generative Deep Learning for Image-to-Image Translation and MRI Reconstruction: A Cross-Domain Reviewcited by 0
  7. 2025Domain Adaptation for Image Classification of Defects in Semiconductor Manufacturingcited by 0