Research map / Video / Video generation
Learning-based Axial Video Motion Magnification
Kwon Byung-Ki, Oh Hyun-Bin, Kim Jun-Seong, Hyunwoo Ha, Tae-Hyun Oh
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 2D convolutions with weight-shared 1D convolutions in the Shape branch and Manipulator (Motion Separation Module) (ablation) | Axial motion magnification network · Generic and axial evaluation datasets, subpixel test | SSIM | Improved |
| replace 2D convolutions with 1D convolutions (MSM) (ablation) | Axial motion magnification network · Generic and axial evaluation datasets, noise test | SSIM | No clear effect |
| add either the angle phi or the magnification map Lambda alone to the DMM-style training data (ablation) | Axial motion magnification network · Generic evaluation dataset, subpixel test | SSIM | No clear effect |
| use both phi and Lambda in the synthetic training data (ablation) | Axial motion magnification network · Generic evaluation dataset, subpixel test | SSIM | Improved |
| add the object-wise magnification map Lambda to the training data (ablation) | Axial motion magnification network · Generic evaluation dataset, noise test | SSIM | Improved |
| add the angle phi to the training data (ablation) | Axial motion magnification network · Generic evaluation dataset, noise test | SSIM | No clear effect |
| use the proposed axial method instead of the modified phase-based baseline | Axial motion magnification · Axial evaluation dataset, subpixel and noise tests | SSIM | Improved |
| use the proposed method versus DMM and STB-VMM for generic magnification | Generic motion magnification · Generic evaluation dataset, subpixel test | SSIM | No clear effect |
Closest papers by meaning
- Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture (CVPR 2024 · similarity 0.90)
- 3D Motion Magnification: Visualizing Subtle Motions from Time-Varying Radiance Fields (ICCV 2023 · similarity 0.90)
- Event-Based Motion Magnification (ECCV 2024 · similarity 0.90)
- Learning-based Video Motion Magnification (ECCV 2018 · similarity 0.90)
- EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer (AAAI 2024 · similarity 0.89)
- Motion Modes: What Could Happen Next? (CVPR 2025 · similarity 0.84)
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.
