Research map / Image generation / GANs
WarpedGANSpace: Finding Non-Linear RBF Paths in GAN Latent Space
Christos Tzelepis, Georgios Tzimiropoulos, Ioannis Patras
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use non-linear RBF warping paths instead of linear directions | latent path discovery · SN-GAN MNIST | reconstructor accuracy (%): 88.0 -> 98.4 | Improved |
| use non-linear RBF warping paths instead of linear directions | latent path discovery · SN-GAN AnimeFaces | reconstructor accuracy (%): 99.0 -> 99.8 | Improved |
| use non-linear RBF warping paths instead of linear directions | latent path discovery · BigGAN ImageNet | reconstructor accuracy (%): 85.0 -> 92.6 | Improved |
| use non-linear RBF warping paths instead of linear directions | latent path discovery · ProgGAN CelebA-HQ | reconstructor accuracy (%): 90.0 -> 99.3 | Improved |
| use non-linear paths instead of linear (Voynov) directions | latent path discovery · ProgGAN yaw correlation | L1-normalized correlation: 0.24 -> 0.32 | Improved |
| use non-linear paths instead of linear (Voynov) directions | latent path discovery · ProgGAN pitch correlation | L1-normalized correlation: 0.25 -> 0.38 | Improved |
| use non-linear paths instead of linear (Voynov) directions | latent path discovery · ProgGAN smile correlation | L1-normalized correlation: 0.57 -> 0.61 | Improved |
| use non-linear paths instead of linear (Voynov) directions | latent path discovery · ProgGAN race correlation | L1-normalized correlation: 0.31 -> 0.29 | Hurt |
| use non-linear paths instead of linear (Voynov) directions | latent path discovery · ProgGAN hair correlation | L1-normalized correlation: 0.36 -> 0.49 | Improved |
| use non-linear paths instead of linear (Voynov) directions | latent path discovery · ProgGAN yaw range | range r (deg): 18.93 -> 43.66 | Improved |
| use non-linear paths instead of linear (Voynov) directions | latent path discovery · ProgGAN pitch range | range r (deg): 8.27 -> 22.53 | Improved |
| use non-linear paths instead of GANSpace PCA directions | latent path discovery · ProgGAN yaw correlation | L1-normalized correlation: 0.27 -> 0.32 | Improved |
Closest papers by meaning
- Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs (ICLR 2022 · similarity 0.91)
- Rayleigh EigenDirections (REDs): Nonlinear GAN Latent Space Traversals for Multidimensional Features (ECCV 2022 · similarity 0.90)
- A Geometric Analysis of Deep Generative Image Models and Its Applications (ICLR 2021 · similarity 0.90)
- The GAN is dead; long live the GAN! A Modern GAN Baseline (NeurIPS 2024 · similarity 0.87)
- NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models (CVPR 2024 · similarity 0.86)
- WeditGAN: Few-Shot Image Generation via Latent Space Relocation (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
