AI Paper Atlas

Research map / Video / Video segmentation and tracking

OMR: Occlusion-Aware Memory-Based Refinement for Video Lane Detection

Dongkwon Jin, Chang-Su Kim

ECCV 2024 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 9 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 the latent obstacle mask to the OMR module (ablation)OMR · VIL-100F1: 0.933 -> 0.936 (R_M 0.043 -> 0.038)Improved
add ConvLSTM memory to the OMR module (ablation)OMR · VIL-100F1: 0.932 -> 0.936 (R_F 0.024 -> 0.026)Mixed
add synthetic KINS-object data augmentation for training OMR (ablation)OMR · VIL-100flickering rate R_F: 0.036 -> 0.026Improved
add synthetic data augmentation (ablation)OMR · VIL-100F1: 0.929 -> 0.936Improved
use OMR instead of RVLDvideo lane detector · VIL-100mIoU: 0.787 -> 0.774Hurt
use OMR instead of RVLDvideo lane detector · VIL-100F1: 0.924 -> 0.936Improved
use OMR instead of RVLDvideo lane detector · OpenLane-VmIoU: 0.727 -> 0.742Improved
use OMR instead of RVLD on flickering ratevideo lane detector · OpenLane-Vflickering rate R_F: 0.014 -> 0.016Hurt
replace RVLD's motion estimator with OMR pipelinevideo lane detector · VIL-100runtime (s per frame): 0.0125s -> 0.0095sImproved

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