Research map / Video / Video segmentation and tracking
PhaseNet for Video Frame Interpolation
Simone Meyer, Abdelaziz Djelouah, Brian McWilliams, Alexander Sorkine-Hornung, Markus Gross, Christopher Schroers
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 PhaseNet instead of SepConv | Video frame interpolation · Challenging scenes with motion blur or lighting changes | visual interpolation quality | Mixed |
| Use PhaseNet instead of Phase | Video frame interpolation · Large-motion and high-frequency scenes | visual interpolation quality | Improved |
| Use PhaseNet instead of MDP-Flow2 | Video frame interpolation · Scenes with lighting changes | visual interpolation quality | Improved |
| Add phase loss to image loss (ablation) | PhaseNet · Video frame interpolation | sharpness | Improved |
| Train with image loss only, removing phase loss (ablation) | PhaseNet · Video frame interpolation | sharpness | Hurt |
| Train with phase loss only, removing image loss (ablation) | PhaseNet · Video frame interpolation | interpolation quality | Hurt |
| Vary the phase-loss weighting factor ν within [0.1, 1] (ablation) | PhaseNet · Video frame interpolation | interpolation quality: ν ∈ [0.1, 1] | No clear effect |
| Reuse trained highest-level weights for additional pyramid levels instead of averaging lower-level phase values (ablation) | PhaseNet · High-resolution interpolation | motion range | Improved |
| Average lower-level phase values instead of reusing trained weights (ablation) | PhaseNet · High-resolution interpolation | motion range | Hurt |
| Use the hierarchical training procedure (ablation) | PhaseNet · Video frame interpolation | training stability | Improved |
Closest papers by meaning
- IM-Net for High Resolution Video Frame Interpolation (CVPR 2019 · similarity 0.90)
- Video Frame Interpolation via Adaptive Separable Convolution (ICCV 2017 · similarity 0.89)
- Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation (CVPR 2018 · similarity 0.88)
- Long-Term Video Frame Interpolation via Feature Propagation (CVPR 2022 · similarity 0.88)
- Video Frame Interpolation via Adaptive Convolution (CVPR 2017 · similarity 0.88)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.86)
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.
