AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Manifold Matching via Deep Metric Learning for Generative Modeling

Mengyu Dai, Haibin Hang

ICCV 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 12 citations (OpenAlex)

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 changedWhereMeasuredEffect
replace GAN loss with manifold matching (MvM)ResNet generator · Set5 (x4 SISR)PSNR: 29.03 -> 29.76Improved
replace GAN loss with manifold matching (MvM)RDN generator · Set5 (x4 SISR)PSNR: 29.07 -> 30.06Improved
replace GAN loss with manifold matching (MvM)NSRNet generator · Set5 (x4 SISR)PSNR: 29.46 -> 29.79Improved
replace GAN loss with manifold matching (MvM)ResNet generator · Set5 (x4 SISR)LPIPS: 0.1885 -> 0.1941Hurt
replace GAN loss with manifold matching (MvM)RDN generator · Urban100 (x4 SISR)LPIPS: 0.2876 -> 0.2566Improved
replace GAN loss with manifold matching (MvM)NSRNet generator · Set5 (x4 SISR)NIQE: 5.7818 -> 6.0846Hurt
use MvM instead of ESRGAN perceptual setupSISR generator · Set5 (x4 SISR)PSNR: 29.63 -> 29.87Improved
use MvM instead of ESRGAN perceptual setupSISR generator · Set5 (x4 SISR)LPIPS: 0.1227 -> 0.1281Mixed
use MvM instead of ESRGAN perceptual setupSISR generator · Set5 (x4 SISR)NIQE: 6.2838 -> 5.8904Improved
use MvM instead of WGAN-GPResNet generator · CelebA 64x64FID: 18.0 -> 11.1Improved
use MvM instead of SWGANResNet generator · LSUN bedroom 64x64FID: 14.9 -> 13.7Improved
match both centroid and 2-diameter instead of either alone (ablation)MvM · CelebA 32x32sample quality (qualitative)Improved

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