Research map / Video / Video segmentation and tracking
Event-based Simultaneous Localization and Mapping: A Comprehensive Survey
Kunping Huang, Sen Zhang, Jing Zhang, Dacheng Tao
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 DMin instead of CMax | CMax · Rotational: boxes | angular velocity error (deg/s): 9.08 -> 7.06 | Improved |
| use approximate DMin instead of DMin (truncated kernel) | DMin · Rotational: shapes | angular velocity error (deg/s): 42.22 -> 55.44 | Hurt |
| use ST-PPP probabilistic model instead of DMin | DMin · Rotational: shapes | angular velocity error (deg/s): 42.22 -> 25.89 | Improved |
| use approximate DMin instead of DMin | DMin · MVSEC outdoor_day1 | APRE (degrees): 9.41 -> 8.04 | Improved |
| use event-by-event online DMin | DMin · MVSEC outdoor_day1 | APRE (degrees): 9.41 -> 13.98 | Hurt |
| use deep learning (Ye et al.) instead of DMin | DMin · MVSEC outdoor_day1 | APRE (degrees): 9.41 -> 3.98 | Improved |
| add inertial data and images (USLAM) to event VO (EVO) | EVO · rpg_desk | positional error (cm): 5.2 -> 9.8 | Hurt |
| use stereo event depth (ESVO) instead of USLAM | USLAM · rpg_monitor | positional error (cm): 6.5 -> 3.3 | Improved |
| use EDS event-image alignment instead of ESVO | ESVO · rpg_monitor | positional error (cm): 3.3 -> 1.0 | Improved |
| add events and IMU (PL-EVIO) to frame VIO (ORB-SLAM3) | ORB-SLAM3 · vicon hdr 1 | positional error (%/m): 0.32 -> 0.17 | Improved |
Closest papers by meaning
- Two-Way Street: Efficient VSLAM using Collaborative In-Sensor and Off-Sensor processing (ECCV 2026 · similarity 0.88)
- Event-based Optical Flow Using Spatio-temporal Registration (TPAMI 2026 · similarity 0.87)
- The Spatio-Temporal Poisson Point Process: A Simple Model for the Alignment of Event Camera Data (ICCV 2021 · similarity 0.86)
- IncEventGS: Pose-Free Gaussian Splatting from a Single Event Camera (CVPR 2025 · similarity 0.86)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.85)
- ETAP: Event-based Tracking of Any Point (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.
