AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Normal Flow Directly From Events

Dehao Yuan, Levi Burner, Jiayi Wu, Minghui Liu, Jingxi Chen, Yiannis Aloimonos, Cornelia Fermüller

ICCV 2025 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 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
replace conventional optical flow loss with the two-term motion field loss (radial plus angular) (ablation)point-based normal flow estimator · ablation (Appendix 11)errorImproved
add uncertainty-score filtering from rotation ensemble (ablation)egomotion estimation · EVIMO2-sfmegomotion errorImproved
add rotation-ensemble uncertainty score (ablation)normal flow estimator · ablationcorrelation of error with uncertaintyImproved
use SVM maximum-margin egomotion solver instead of depth-positivity maximizationegomotion from normal flow · EVIMO2-sfm 03 02 0RMS V (m/s): 0.500 -> 0.227Improved
use SVM solver instead of depth-positivity methodegomotion from normal flow · EVIMO2-sfm 03 04 0RMS V (m/s): 0.217 -> 0.136Improved
use SVM solver instead of depth-positivity methodegomotion from normal flow · EVIMO2-sfm 03 02 3RMS V (m/s): 0.213 -> 0.279Hurt
use point-based VecKM estimator instead of PointNet (both supervised)normal flow estimation · EVIMO2-imo averagePEE: 0.933 -> 0.423Improved
use point-based supervised estimator instead of frame-based self-supervised TCMnormal flow estimation · MVSEC averagePEE: 0.516 -> 0.992Hurt
use point-based estimator instead of frame-based TCMnormal flow estimation · EVIMO2-imo averagePEE: 1.105 -> 0.396Improved
train on union of MVSEC, DSEC and EVIMO instead of single datasetnormal flow estimator · MVSEC averagePEE: 1.419 -> 0.992Improved
train on DSEC single scene instead of MVSECnormal flow estimator · DSEC 8 day scenesPEE: 1.631 -> 1.043Improved
evaluate at night instead of daynormal flow estimator trained on DSEC · DSECPEE: 1.043 -> 1.357Hurt

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