Research map / 3D vision / 3D generation
Reflection-Aware Reasoning for Non-Line-of-Sight Pedestrian Localization
Byeonggyu Park, Mingu Jeon, Seong-Woo Kim
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 |
|---|---|---|---|
| use the proposed reflection-aware framework instead of Park et al. [24] for NLOS pedestrians | Proposed · NLOS localization, ego-static | average localization error (m): 1.69 -> 1.01 | Improved |
| use the proposed framework instead of Park et al. [24] for NLOS pedestrians | Proposed · NLOS localization, ego-dynamic | average localization error (m): 3.23 -> 1.23 | Improved |
| use the proposed framework instead of Scheiner et al. [27] for LOS pedestrians | Proposed · LOS localization, ego-dynamic | average localization error (m): 1.36 -> 0.54 | Improved |
| use proposed segmentation instead of Wu et al. [34] under ego-dynamic conditions | Proposed · Reflection-type point segmentation (ego-dynamic) | Macro-F1: 0.481 -> 0.814 | Improved |
| use proposed segmentation instead of Wu et al. [34] under ego-static conditions | Proposed · Reflection-type point segmentation (ego-static) | Macro-F1: 0.890 -> 0.915 | Improved |
| move from ego-static to ego-dynamic driving | Proposed · NLOS localization | average localization error (m): 1.01 -> 1.23 | Hurt |
| ego-dynamic vs ego-static for 3rd-bounce pedestrian class | Proposed · 3rd-bounce pedestrian class | F1-score: 0.916 -> 0.731 | Hurt |
| inaccurate reflective surface estimation despite accurate reflection-point detection | Proposed · NLOS localization | localization error | Hurt |
Closest papers by meaning
- Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar (CVPR 2020 · similarity 0.84)
- RadarMOSEVE: A Spatial-Temporal Transformer Network for Radar-Only Moving Object Segmentation and Ego-Velocity Estimation (AAAI 2024 · similarity 0.82)
- Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information (ECCV 2024 · similarity 0.82)
- LINK: Learning to Localize from Known to Unknown Scenes (NeurIPS 2026 · similarity 0.81)
- BEVSpread: Spread Voxel Pooling for Bird's-Eye-View Representation in Vision-based Roadside 3D Object Detection (CVPR 2024 · similarity 0.80)
- Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving (NeurIPS 2026 · similarity 0.80)
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.
