AI Paper Atlas

Research map / Image generation / GANs

Sphere Generative Adversarial Network Based on Geometric Moment Matching

CVPR 2019 · Image generation › GANs · approach: Stabilized GAN training · 40 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 changedWhereMeasuredEffect
Use Sphere GAN-ResNet instead of Spectral NormCIFAR-10 image generation · CIFAR-10IS: 7.96 ± .06 -> 8.39 ± .08Helped
Use Sphere GAN-ResNet instead of Spectral NormCIFAR-10 image generation · CIFAR-10FID: 22.5 -> 17.1Helped
Use Sphere GAN-ResNet instead of Spectral NormSTL-10 image generation · STL-10IS: 9.10 ± .04 -> 9.55 ± .11Helped
Use Sphere GAN-ResNet instead of Spectral NormSTL-10 image generation · STL-10FID: 40.1 -> 31.4Helped
Use Sphere GAN instead of MMD-GAN-rqLSUN Bedroom image generation · LSUN BedroomFID: 32.0 -> 16.9Helped
Use higher-order moment matching rather than only lower-order moments (ablation)Sphere GAN on CIFAR-10 with ConvNet · CIFAR-10ISHelped
Use moments higher than fifth order (ablation)Sphere GAN on CIFAR-10 · CIFAR-10ISHurt
Increase the hypersphere dimension (ablation)Sphere GAN on CIFAR-10 with ConvNet · CIFAR-10ISHelped

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy