Research map / Image generation / GANs
Manifold-Valued Image Generation with Wasserstein Generative Adversarial Nets
Zhiwu Huang, Jiqing Wu, Luc Van Gool
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 |
|---|---|---|---|
| Replace the standard WGAN objective with manifold-aware Wasserstein training for HSV generation | WGAN-HSV · CIFAR-10 HSV | FID: 38.4 -> 27.2 | Improved |
| Replace the standard WGAN objective with manifold-aware Wasserstein training for HSV generation | WGAN-HSV · ImageNet HSV | FID: 76.7 -> 68.4 | Improved |
| Replace the standard WGAN objective with manifold-aware Wasserstein training for CB chromaticity generation | WGAN-CB · CIFAR-10 CB | FID: 80.7 -> 59.4 | Improved |
| Replace the standard WGAN objective with manifold-aware Wasserstein training for CB chromaticity generation | WGAN-CB · ImageNet CB | FID: 101.3 -> 89.2 | Improved |
| Generate HSV images with manifold-aware WGAN rather than a direct RGB GAN | WGAN-RGB · CIFAR-10 | FID: 29.3 -> 27.2 | Improved |
| Generate HSV images with manifold-aware WGAN rather than a direct RGB GAN | WGAN-RGB · ImageNet | FID: 71.2 -> 68.4 | Improved |
Closest papers by meaning
- Flow-based Generative Models for Learning Manifold to Manifold Mappings (AAAI 2021 · similarity 0.87)
- Banach Wasserstein GAN (NeurIPS 2018 · similarity 0.87)
- A Geometric Analysis of Deep Generative Image Models and Its Applications (ICLR 2021 · similarity 0.86)
- InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models (AAAI 2020 · similarity 0.86)
- On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds (NeurIPS 2022 · similarity 0.86)
- A Two-Step Computation of the Exact GAN Wasserstein Distance (ICML 2018 · similarity 0.85)
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.
