AI Paper Atlas

Research map / 3D vision / Depth and stereo

Ev-iCRF: Self-supervised Event-guided iCRF Estimation for HDR Image Reconstruction

Xucheng Guo, Bing Li, Lin Wang, Yiran Shen

AAAI 2026 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 1 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 Complementary Mask-Driven optimization stage after initialization (ablation)Ev-iCRF · EventHDR (2000 test images) ablationmu-PSNR: 19.73 -> 20.58Improved
add event-guided initialization before optimization (ablation)Ev-iCRF · EventHDR (2000 test images) ablationmu-PSNR: 14.13 -> 20.58Improved
use ground-truth HDR edge supervision instead of event self-supervision (ablation)Ev-iCRF · EventHDR (2000 test images)mu-PSNR: 20.58 -> 22.58 PSNR; SSIM 0.79 -> 0.75Mixed
self-supervised event-guided iCRF vs best supervised baselineEv-iCRF · EventHDR (2000 test images)mu-PSNR: 14.92 -> 20.58Improved
train on synthetic data only and test on real EventHDREv-iCRF · EventHDR (2000 test images)mu-PSNR: 20.58 -> 15.83Hurt
use event-guided iCRF vs non-learning CLAHEEv-iCRF · EventHDR (2000 test images)mu-SSIM: 0.67 -> 0.79Improved

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