Research map / 3D vision / Gaussian splatting
3D Motion Magnification: Visualizing Subtle Motions from Time-Varying Radiance Fields
Brandon Y. Feng, Hadi Alzayer, Michael Rubinstein, William T. Freeman, Jia-bin Huang
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 |
|---|---|---|---|
| magnify tri-plane feature embeddings instead of rendered video frames (ablation) | 3D motion magnification with NeRF · Synthetic Blender scenes | SSIM / LPIPS vs ground-truth magnified frames | Improved |
| use phase-based instead of linear magnification on tri-plane features (ablation) | Tri-plane NeRF magnification · Synthetic Blender scenes | magnification quality under noise | Improved |
| linear Eulerian magnification on tri-plane instead of phase-based (ablation) | Tri-plane NeRF magnification · Synthetic Blender scenes | visual artifacts | Hurt |
| increase deviation of test view from observed views, embedding-space vs color-space magnification (ablation) | Embedding-space magnification · Synthetic Blender scenes | magnification quality | Improved |
| encoding shift (separate phase shift per frequency) instead of position shift in positional-encoding NeRF (ablation) | NeRF with positional encoding · Synthetic Blender scenes | magnification quality | Improved |
| 3D magnification handles handheld camera motion, versus 2D video magnification | 3D motion magnification · Real-world single-camera handheld videos | qualitative magnification | Improved |
Closest papers by meaning
- EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer (AAAI 2024 · similarity 0.90)
- Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture (CVPR 2024 · similarity 0.88)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.86)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.86)
- MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field (ICLR 2024 · similarity 0.85)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · 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.
