atlas

Research map / Image generation / Autoregressive and latent generation

Geometric Structure Preserving Warp for Natural Image Stitching

CVPR 2022 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 64 citations (OpenAlex)

Check 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
Add large-scale geometric structure preservation to GSPGSP image stitching · 50 diversified stitching datasetsgeometric structure preservationHelped
Use adapted sampling-point weights instead of equal weights (ablation)GES-GSP · Image stitching with overlapping and non-overlapping regionsstitching naturalness and distortionHelped
Use equal weights for geometric-structure sampling points (ablation)GES-GSP · Image stitching with overlapping regionsstitching naturalnessHurt
Increase sampling density to more than one point per grid (ablation)GES-GSP · Image stitching with geometric structures spanning multiple gridsgeometric structure preservationHelped
Reduce sampling density to one point every two or four grids (ablation)GES-GSP · Image stitching with geometric structures spanning multiple gridsgeometric structure preservationHurt
Add the unweighted geometric-structure constraint (ablation)GSP · Image stitchingbalance between local alignment and structure preservationHurt

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