AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Semantic-Guided Multi-Mask Image Harmonization

Xuqian Ren, Yifan Liu

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 15 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
predict operator masks instead of regressing RGB directly (ablation)Sg-MMH · HSceneMSE: 141.75 -> 99.84Improved
predict operator masks instead of regressing RGB directly (ablation)Sg-MMH · HScenePSNR: 28.73 -> 30.59Improved
predict operator masks instead of regressing RGB directly (ablation)Sg-MMH · HLIPMSE: 75.45 -> 48.02Improved
predict operator masks instead of regressing RGB directly (ablation)Sg-MMH · HLIPPSNR: 31.34 -> 33.11Improved
add patch discriminator with relativistic GAN loss to operator-mask generator (ablation)Sg-MMH (OM) · HSceneMSE: 99.84 -> 94.00Improved
add patch discriminator with relativistic GAN loss to operator-mask generator (ablation)Sg-MMH (OM) · HScenePSNR: 30.59 -> 30.88Improved
add patch discriminator with relativistic GAN loss to operator-mask generator (ablation)Sg-MMH (OM) · HLIPMSE: 48.02 -> 42.62Improved
add patch discriminator with relativistic GAN loss to operator-mask generator (ablation)Sg-MMH (OM) · HLIPLPIPS: 0.021 -> 0.018Improved
predict operator masks instead of regressing RGB directly (ablation)Sg-MMH · HSceneSSIM: 0.95 -> 0.96Improved
predict operator masks instead of regressing RGB directly (ablation)Sg-MMH · HLIPLPIPS: 0.025 -> 0.021Improved
direct RGB regression versus the composite inputSg-MMH (RGB) · HLIPLPIPS: 0.021 -> 0.025Hurt
use Sg-MMH(OMGAN) instead of DoveNet, BarginNet or RainNet on real compositesSg-MMH (OMGAN) · Real composited images (user study)user study score (%): 36.7 vs 20.6, 24.2, 18.5Improved

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