atlas

Research map / Image generation / Image restoration

Pixel-Wise Warping for Deep Image Stitching

AAAI 2023 · Image generation › Image restoration · approach: Image harmonization and color transformation · 23 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 homography-based warping with pixel-wise warpingimage stitching · PDIS validationPSNR: 31.4430 -> 34.8244Helped
replace homography-based warping with pixel-wise warpingimage stitching · PDIS validationLPIPS: 0.0341 -> 0.0066Helped
replace homography-based warping with pixel-wise warpingimage stitching · UDIS datasetPSNR: 21.1715 -> 23.3109Helped
add epipolar loss to warp estimation (ablation)PWM · PDIS target image, total regionAED: 8.86 -> 8.08Helped
add epipolar loss to warp estimation (ablation)PWM · PDIS target image, total regionLP: 1.48 -> 1.51Hurt
add line-preservation loss to warp estimation (ablation)PWM with epipolar loss · PDIS target image, total regionLP: 1.51 -> 1.27Helped
add GT Warp branch (ablation)SIGMo · PDIS whole regionLPIPS: 0.1746 -> 0.1220Helped
add Domain Adaptation branch (ablation)SIGMo with PW+GW branches · UDIS reference regionPSNR: 32.05 -> 35.53Helped

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