mlsanityData to 7 Oct 2026

Optimizing Latent Space Directions For GAN-based Local Image Editing

arXiv 2111.12583 ↗First posted 24 Nov 2021cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Generative Adversarial Network (GAN) based localized image editing can suffer from ambiguity between semantic attributes. We thus present a novel objective function to evaluate the locality of an image edit. By introducing the supervision from a pre-trained segmentation network and optimizing the objective function, our framework, called Locally Effective Latent Space Direction (LELSD), is applicable to any dataset and GAN architecture. Our method is also computationally fast and exhibits a high extent of disentanglement, which allows users to interactively perform a sequence of edits on an image. Our experiments on both GAN-generated and real images qualitatively demonstrate the high quality and advantages of our method.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 25 of its 27 references that are in the map. First posted on arXiv 24 Nov 2021.

Builds on

25 of 27 references.

References · 25

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  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. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  6. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  7. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  8. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  9. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  10. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  11. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  12. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
13 more
  1. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  2. 2019On the "steerability" of generative adversarial networkscited by 247
  3. 2019GANalyze: Toward Visual Definitions of Cognitive Image Propertiescited by 193
  4. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  5. 2020Rewriting a Deep Generative Modelcited by 105
  6. 2020Controlling generative models with continuous factors of variationscited by 93
  7. 2021Using latent space regression to analyze and leverage compositionality in GANscited by 55
  8. 2021Low-Rank Subspaces in GANscited by 52
  9. 2021Linear Semantics in Generative Adversarial Networkscited by 25
  10. 2020GarmentGAN: Photo-realistic Adversarial Fashion Transfercited by 16
  11. 2021Barbershop: GAN-based Image Compositing using Segmentation Maskscited by 14
  12. 2021Decorating Your Own Bedroom: Locally Controlling Image Generation with Generative Adversarial Networkscited by 8
  13. 2019Aesthetics of Neural Network Artcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4.

5 papers.

  1. 2023A Unified Framework for Generative Data Augmentation: A Comprehensive Surveycited by 4
  2. 2023Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulationscited by 2
  3. 2022Discovering Class-Specific GAN Controls for Semantic Image Synthesiscited by 1
  4. 20233D GANs and Latent Space: A comprehensive surveycited by 1
  5. 2023Editable Stain Transformation Of Histological Images Using Unpaired GANscited by 1