AI Paper Atlas

Research map / Video / Video generation

Deep Learning-Based Image and Video Inpainting: A Survey

Weize Quan, J. Chen, Yanli Liu, Dong-ming Yan A, Peter Wonka

IJCV 2024 · Video › Video generation · approach: Diffusion-based video editing · 108 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 style loss (ablation)inpainting network with pixel loss · CelebA-HQ, mask 20%-30%FID: 3.31 -> 2.25Improved
add style loss (ablation)inpainting network with pixel loss · CelebA-HQ, mask 20%-30%PSNR: 30.76 -> 30.24Hurt
add perceptual loss (VGG16) (ablation)inpainting network with pixel loss · CelebA-HQ, mask 20%-30%FID: 3.31 -> 3.20Improved
add perceptual loss (VGG16) (ablation)inpainting network with pixel loss · CelebA-HQ, mask 20%-30%LPIPS: 0.063 -> 0.057Improved
add perceptual loss from segmentation ResNet50 (ablation)inpainting network with pixel loss · CelebA-HQ, mask 20%-30%LPIPS: 0.063 -> 0.052Improved
add LSGAN adversarial loss (ablation)inpainting network with pixel loss · CelebA-HQ, mask 20%-30%LPIPS: 0.063 -> 0.054Improved
add LSGAN adversarial loss (ablation)inpainting network with pixel loss · CelebA-HQ, mask 20%-30%FID: 3.31 -> 3.34No clear effect
combine perceptual and style loss instead of style alone (ablation)inpainting network with pixel loss · CelebA-HQ, mask 20%-30%FID: 2.25 -> 2.26No clear effect
add style loss (ablation)inpainting network with pixel loss · Paris StreetView, mask 20%-30%FID: 26.55 -> 19.65Improved
use LGNet instead of MATimage inpainting · Places2, mask 20%-30%PSNR: 26.41 -> 28.18Improved
use diffusion-based RePaint instead of LGNetimage inpainting · CelebA-HQ, mask 20%-30%PSNR: 30.54 -> 28.38Hurt

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