AI Paper Atlas

Research map / Image generation / GANs

MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

Andranik Sargsyan, Shant Navasardyan, Xingqian Xu, Humphrey Shi

ICCV 2023 · Image generation › GANs · approach: Large-scale GAN latent analysis · 42 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
add online model re-parametrization to the baseline (ablation)MI-GAN 256 · Places2 256FID: 14.94 -> 12.22Improved
add knowledge distillation from Co-Mod-GAN on painting-branch outputs (ablation)MI-GAN 256 with re-param · Places2 256FID: 12.22 -> 11.83Improved
add re-parametrization and distillation to baseline (ablation)MI-GAN 256 · Places2 256LPIPS: 0.407 -> 0.39Improved
MI-GAN versus LaMa on Places2 256 FIDMI-GAN · Places2 256FID: 22.00 -> 11.83Improved
MI-GAN versus Co-Mod-GAN and SH-GAN on FIDMI-GAN · Places2 256FID: 9.32 -> 11.83Hurt
use MI-GAN instead of Co-Mod-GAN on mobile CPUsMI-GAN · iPhone7 256inference time (ms): 4475.33 -> 1030.25Improved
MI-GAN versus teacher-class models at 512 resolutionMI-GAN 512 · Places2 512FID: 7.03 -> 10.00Mixed

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