Research map / Video / Video segmentation and tracking
An Asynchronous Linear Filter Architecture for Hybrid Event-Frame Cameras
Ziwei Wang, Yonhon Ng, Cedric Scheerlinck, Robert E. Mahony
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 |
|---|---|---|---|
| replace complementary filter gain with asynchronous Kalman gain | CF · HDR dataset | MSE (x1e-2): 2.37 -> 1.84 | Improved |
| replace complementary filter gain with asynchronous Kalman gain | CF · AHDR dataset | MSE (x1e-2): 4.25 -> 3.94 | Improved |
| replace complementary filter gain with asynchronous Kalman gain | CF · HDR dataset | Q-score: 5.17 -> 6.04 | Improved |
| replace complementary filter gain with asynchronous Kalman gain | CF · IJRR DAVIS (mean) | MSE (x1e-2): 0.21 -> 0.18 | Improved |
| replace complementary filter gain with asynchronous Kalman gain | CF · IJRR DAVIS (mean) | LPIPS: 0.19 -> 0.19 | No clear effect |
| use events plus frames (AKF) instead of pure-event E2VID | AKF · HDR/AHDR dataset | MSE: reduction of 71.5% | Improved |
| use AKF instead of Han et al. event-frame network | AKF · HDR/AHDR dataset | MSE: reduction of 69.4% | Improved |
| add frame augmentation (deblur and temporal interpolation) to AKF (ablation) | AKF · fast-motion Shapes_6dof | qualitative | Improved |
| add frame augmentation to CF (ablation) | CF · Tree_rotation (HDR) | qualitative | No clear effect |
| add per-pixel Kalman gain (ablation) | CF · Tree_rotation (HDR) | qualitative | Improved |
| add Kalman gain without frame augmentation (ablation) | AKF · Shapes_6dof | qualitative | No clear effect |
| add AKF filter state memory over EDI deblurring alone (ablation) | AKF · Interlaken_01a | qualitative | Improved |
Closest papers by meaning
- An Asynchronous Kalman Filter for Hybrid Event Cameras (ICCV 2021 · similarity 0.94)
- EventHDR: From Event to High-Speed HDR Videos and Beyond (TPAMI 2024 · similarity 0.89)
- Learning to Super Resolve Intensity Images From Events (CVPR 2020 · similarity 0.89)
- E2SRI: Learning to Super-Resolve Intensity Images From Events (TPAMI 2021 · similarity 0.89)
- Learning To Reconstruct High Speed and High Dynamic Range Videos From Events (CVPR 2021 · similarity 0.88)
- Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging (CVPR 2020 · similarity 0.88)
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.
