Research map / Video / Video segmentation and tracking
Multi Domain Learning for Motion Magnification
Jasdeep Singh, Subrahmanyam Murala, G. Sankara Raju Kosuru
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 multi-domain phase and spatial processing | D1 and D2 · synthetic videos | MSE | Improved |
| use multi-domain phase and spatial processing | D1 and D2 · real-world videos | motion magnification with distortions | Improved |
| add the FDMM block (ablation) | D1 · synthetic videos | MSE | Improved |
| add phase and amplitude loss (ablation) | D1 · synthetic videos | MSE | Improved |
| add the RMTE block (ablation) | D1 · synthetic videos | MSE | Improved |
| add spatial attention ψ to RMTE (ablation) | D1 · synthetic videos | MSE | Improved |
| use FCB-based MSTG rather than a simple U-net-like decoder with residual blocks (ablation) | D1 · synthetic videos | MSE | Improved |
| use multi-scale rather than single-scale texture generation (ablation) | D1 · synthetic videos | MSE | Improved |
| reduce the model from D1 to D2 | proposed network · dynamic real-world scenarios | texture quality | Hurt |
Closest papers by meaning
- Learning-based Video Motion Magnification (ECCV 2018 · similarity 0.90)
- Event-Based Motion Magnification (ECCV 2024 · similarity 0.88)
- 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 0.84)
- MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI (NeurIPS 2024 · similarity 0.81)
- Motion Blur Decomposition with Cross-shutter Guidance (CVPR 2024 · similarity 0.81)
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.
