mlsanityData to 7 Oct 2026

Image Shape Manipulation from a Single Augmented Training Sample

arXiv 2109.06151 ↗First posted 13 Sep 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network. Our method is shown to achieve remarkable performance on image manipulation tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 46 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

32 of 46 references.

References · 32

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  5. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  6. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  7. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  8. 2017Deep Image Priorcited by 1,097
  9. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  10. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  11. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  12. 2018Video-to-Video Synthesiscited by 388
20 more
  1. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  2. 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
  3. 2017Toward Multimodal Image-to-Image Translationcited by 295
  4. 2017VITON: An Image-based Virtual Try-on Networkcited by 285
  5. 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
  6. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  7. 2019Few-shot Video-to-Video Synthesiscited by 196
  8. 2016Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networkscited by 192
  9. 2019Data augmentation using learned transformations for one-shot medical image segmentationcited by 138
  10. 2018SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesiscited by 81
  11. 2019A critical analysis of self-supervision, or what we can learn from a single imagecited by 75
  12. 2018Non-Stationary Texture Synthesis by Adversarial Expansioncited by 66
  13. 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
  14. 2020Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondencecited by 53
  15. 2016Texture Synthesis with Spatial Generative Adversarial Networkscited by 45
  16. 2020Interactive Video Stylization Using Few-Shot Patch-Based Trainingcited by 43
  17. 2020TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Imagescited by 23
  18. 2016WarpNet: Weakly Supervised Matching for Single-view Reconstructioncited by 22
  19. 2019Adversarial Learning of General Transformations for Data Augmentationcited by 2
  20. 2018InGAN: Capturing and Remapping the "DNA" of a Natural Imagecited by 1

Built on by

Not cited yet.