mlsanityData to 14 Oct 2026

Towards Kinetic Manipulation of the Latent Space

arXiv 2409.09867 ↗First posted 15 Sep 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The latent space of many generative models are rich in unexplored valleys and mountains. The majority of tools used for exploring them are so far limited to Graphical User Interfaces (GUIs). While specialized hardware can be used for this task, we show that a simple feature extraction of pre-trained Convolutional Neural Networks (CNNs) from a live RGB camera feed does a very good job at manipulating the latent space with simple changes in the scene, with vast room for improvement. We name this new paradigm Visual-reactive Interpolation, and the full code can be found at https://github.com/PDillis/stylegan3-fun.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 34 references that are in the map. First posted on arXiv 15 Sep 2024.

Builds on

26 of 34 references.

References · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2022Generative Adversarial Networkscited by 5,627
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  11. 2019Searching for MobileNetV3cited by 1,994
  12. 2023Consistency Modelscited by 1,822
14 more
  1. 2024Depth Anything V2cited by 1,422
  2. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  3. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  4. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  5. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  6. 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
  7. 2015A Neural Algorithm of Artistic Stylecited by 483
  8. 2016Adversarial Feature Learningcited by 350
  9. 2023DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editingcited by 294
  10. 2019Large Scale Adversarial Representation Learningcited by 239
  11. 2020A2D2: Audi Autonomous Driving Datasetcited by 190
  12. 2023Real-time Animation Generation and Control on Rigged Models via Large Language Modelscited by 5
  13. 2021Discriminator Synthesis: On reusing the other half of Generative Adversarial Networkscited by 1
  14. 2023Combating the "Sameness" in AI Art: Reflections on the Interactive AI Installation Fencing Hallucinationcited by 1

Built on by

Not cited yet.