Research map / Video / Video segmentation and tracking
LiFR-Seg: Anytime High-Frame-Rate Segmentation via Event-Guided Propagation
Xiaoshan Wu, Xiaoyang Lyu, Yifei Yu, Bo Wang, Zhongrui Wang, Xiaojuan Qi
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add uncertainty-aware ScoreNet to warping (ablation) | LiFR-Seg · DSEC | mIoU: 72.74 -> 73.82 | Improved |
| add ScoreNet (ablation) | LiFR-Seg · DSEC-Night (zero-shot) | mIoU: 41.46 -> 41.86 | Improved |
| warp deep features instead of images (ablation) | LiFR-Seg · DSEC | mIoU: 72.37 -> 73.82 | Improved |
| warp features instead of segmentation predictions (ablation) | LiFR-Seg · DSEC | mIoU: 71.63 -> 73.82 | Improved |
| add temporal memory module (dt=50 ms) (ablation) | LiFR-Seg · DSEC | mIoU: 73.49 -> 73.82 | Improved |
| add temporal memory module (dt=800 ms) (ablation) | LiFR-Seg · DSEC | mIoU: 57.33 -> 59.55 | Improved |
| replace E-RAFT with coarser or other flow estimators (ablation) | LiFR-Seg · DSEC | mIoU: 73.82 -> 73.49 (E-RAFT-Lite 1/16) | No clear effect |
| use flow network pretrained on MVSEC instead of DSEC (ablation) | LiFR-Seg · DSEC | mIoU: -0.14 mIoU | No clear effect |
| propagate features with event motion instead of fusing events with RGB | LiFR-Seg vs CMNeXt · M3ED-Drone | mIoU: 59.56 -> 64.28 | Improved |
| use interpolation then segmentation instead of LFR baseline | TLX + Seg. · SHF-DSEC | mIoU: 61.73 -> 55.89 | Hurt |
Closest papers by meaning
- Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach (AAAI 2025 · similarity 0.89)
- ESS: Learning Event-Based Semantic Segmentation from Still Images (ECCV 2022 · similarity 0.88)
- ESEG: Event-Based Segmentation Boosted by Explicit Edge-Semantic Guidance (AAAI 2025 · similarity 0.87)
- Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation (AAAI 2024 · similarity 0.86)
- Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes (CVPR 2024 · similarity 0.85)
- High Temporal Consistency through Semantic Similarity Propagation in Semi-Supervised Video Semantic Segmentation for Autonomous Flight (CVPR 2025 · similarity 0.85)
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.
