AI Paper Atlas

Research map / Image generation / Image restoration

Wide-Angle Rectification via Content-Aware Conformal Mapping

Qi Zhang, Hongdong Li, Qing Wang

CVPR 2023 · Image generation › Image restoration · approach: Image harmonization and color transformation · 5 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
Remove boundary preservation term (EB) from the full method (ablation)polar-form LSCM rectification · Quantitative evaluation (Table 1)ConformalAcc, ShapeAcc, StraightAcc: ConformalAcc 0.8259->0.8458; ShapeAcc 0.9683->0.9736; StraightAcc 0.9864->0.9872Mixed
Polar-form conformal mapping (ours) instead of Carroll's Cartesian/Mercator conformal mappingwide-angle rectification · Quantitative evaluation (Table 1)ShapeAcc and ConformalAcc: ShapeAcc 0.9407->0.9683; ConformalAcc 0.7639->0.8259Improved
Polar-form conformal mapping (ours) vs Shih's facial-region rectificationwide-angle rectification · Quantitative evaluation (Table 1)StraightAcc: 0.9907 (Shih) vs 0.9864 (ours)Hurt
Proposed content-aware polar LSCM rectification vs perspective, Mercator, stereographic, and Carroll's methodswide-angle rectification · User study on 150 Flickr wide-angle images (60 participants)user preference rate: 95.2%, 91.6%, 86.5%, 74.3% preferenceImproved

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