Research map / Video / Video segmentation and tracking
Event-Based Motion Magnification
Yutian Chen, Shi Guo, Yu Fangzheng, Feng Zhang, Jinwei Gu, Tianfan Xue
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 event stream plus low-frame-rate RGB instead of a high-speed RGB camera | motion magnification system · SM-ERGB-Synth test | PSNR: 22.30 -> 22.32 PSNR with about 20% of the data volume | Improved |
| train end-to-end instead of event interpolation (TimeLens) followed by LVMM magnification | event-based magnification · SM-ERGB-Synth test | PSNR: 17.60 -> 22.32 | Improved |
| use our network with manipulator and SRP instead of retrained REFID | event-based magnification · SM-ERGB-Synth test | PSNR: 19.64 -> 22.32 | Improved |
| add Second-order Recurrent Propagation instead of first-order propagation (ablation) | Ours · SM-ERGB-Synth (long interpolation sequences) | visual quality / blur | Improved |
| add temporal band-pass filter at inference (ablation) | Ours · real tuning fork sequence | motion regularity / noise | Improved |
| add texture loss and shape loss (ablation) | Ours · SM-ERGB-Synth (90 magnified frames) | visual quality | Improved |
| test with Lanczos downsampling instead of bicubic used in training (ablation) | Ours · SM-ERGB-Synth test | PSNR: 22.2444 -> 22.2402 | No clear effect |
Closest papers by meaning
- Learning-based Axial Video Motion Magnification (ECCV 2024 · similarity 0.90)
- Learning-based Video Motion Magnification (ECCV 2018 · similarity 0.90)
- Self-Supervised Motion Magnification by Backpropagating Through Optical Flow (NeurIPS 2023 · similarity 0.89)
- Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture (CVPR 2024 · similarity 0.88)
- EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer (AAAI 2024 · similarity 0.87)
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.87)
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.
