AI Paper Atlas

Research map / Image generation / Super-resolution

Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation

Lingzhi Zhang, Connelly Barnes, Kevin Wampler, Sohrab Amirghodsi, Eli Shechtman, Zhe Lin, Jianbo Shi

ECCV 2022 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 6 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 pretraining on real-vs-fake classification (ablation)curation network · Human paired preference dataaccuracy: 53.9% -> 56.4%Improved
add JPEG, rotation and noise augmentations (ablation)curation network · Human paired preference dataaccuracy: 53.8% -> 56.4%Improved
input the hole mask (ablation)curation network · Human paired preference dataaccuracy: 52.6% -> 56.4%Improved
use shared-backbone pairwise architecture instead of early fusion (ablation)curation network · Human paired preference dataaccuracy: 51.4% -> 56.4%Improved
fine-tune the backbone instead of freezing it (ablation)curation network · Human paired preference dataaccuracy: 43.7% -> 56.4%Improved
use curation network instead of random choice among 8 guided PatchMatch results (ablation)SuperCAF · 4K+ inpainting benchmark, 100 user-study photosFID: 19.7704 -> 18.7414Improved
use SuperCAF instead of Photoshop Content-Aware FillSuperCAF · 4K+ inpainting benchmark, 100 user-study photosFID: 23.0068 -> 18.7414Improved
replace Real-ESRGAN upsampling with our guided PatchMatch framework on LaMaLaMa · 4K+ inpainting benchmarkFID: 19.2022 -> 18.7414Improved
replace Real-ESRGAN upsampling with our framework on CoModGANCoModGAN · 4K+ inpainting benchmarkFID: 24.8189 -> 19.9224Improved
run deep inpainting on full image instead of auto-crop (ablation)CoModGAN · 4K+ inpainting benchmarkFID: 25.05 -> 24.8No clear effect
use Real-ESRGAN instead of bicubic upsampling (ablation)LaMa · 4K+ inpainting benchmarkFID: 23.66 -> 19.20Improved
use Real-ESRGAN instead of reference-based TTSR upsampling (ablation)LaMa · 4K+ inpainting benchmark (650-image subset)FID: 25.93 -> 25.03Improved

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