AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Distilling Quasi-Conformal Mapping: A Generalizable and Efficient Solution for Wide-Angle Correction

Chengyang Liu, Zixuan Lin, Miaolin Han, Michael K. Ng, Huibin Li

CVPR 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Few-shot and metric distillation

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
distill quasi-conformal LBS-PGD teacher into QDWC-Net studentQDWC-Net · Tan's test setinference latency: 26.33 s -> 0.81 s (96.92% reduction)Improved
use annotation-free distilled network instead of Yao et al. trained on 5,133 labelled pairsQDWC-Net · Tan's test setFaceAcc: 98.536 -> 98.619Improved
use QDWC-Net instead of Yao et al.wide-angle correction · Tan's test setLineAcc: 70.721 (Yao) vs 70.299Hurt
use QDWC-Net instead of Yao et al.wide-angle correction · Tan's test setBodyAcc: 97.081 -> 97.843Improved
apply QDWC-Net trained on Tan's data to unseen Zhu's datasetQDWC-Net · Zhu's datasetLineAcc: 88.563 -> 88.627 vs YaoImproved
use QDWC-Net instead of Shih et al. on Zhu's datasetwide-angle correction · Zhu's datasetFaceAcc: 99.428 (Shih) vs 98.972Hurt
vary number of Mamba layers, loss terms (Lflow, Limg, Lssim) and output head design (ablation)QDWC-Net · Tan's test setcorrection accuracyImproved

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