AI Paper Atlas

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

Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data

Gang Fu, Qing Zhang, Lei Zhu, Chunxia Xiao, Ping Li

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance segmentation · 19 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 specular-free refinement and tone correction stages after physics-based stage (ablation)three-stage network · SHIQPSNR: 20.309 -> 25.575Improved
add specular-free refinement stage (ablation)three-stage network · PSDPSNR: 18.932 -> 22.759Improved
add tone correction stage (ablation)three-stage network · SHIQPSNR: 24.930 -> 25.575Improved
add tone correction stage (ablation)three-stage network · SSHR (synthetic)PSNR: 28.903 -> 28.633Hurt
add specular-free refinement stage (ablation)three-stage network · SSHR (synthetic)PSNR: 24.231 -> 28.903Improved
train on large-scale synthetic SSHR data and test on real imagesspecular highlight removal network · real web images user studyuser scoreImproved

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