Research map / Video / Video segmentation and tracking
IM-Net for High Resolution Video Frame Interpolation
Tomer Peleg, Pablo Szekely, Doron Sabo, Omry Sendik
Check 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 IM-Net instead of TOFlow | Vimeo 1344 × 768 · Vimeo 1344 × 768 | PSNR: 30.54 -> 33.11 | Improved |
| use IM-Net instead of SepConv - Lf | Vimeo 1344 × 768 · Vimeo 1344 × 768 | SSIM: 0.9309 -> 0.9436 | Improved |
| increase resolution from 448 × 256 to 1344 × 768 | IM-Net · Vimeo | PSNR: 33.50 -> 33.11 | Hurt |
| increase resolution from 448 × 256 to 1344 × 768 | SepConv - Lf · Vimeo | PSNR: 33.45 -> 31.81 | Hurt |
| increase resolution from 448 × 256 to 1344 × 768 | TOFlow · Vimeo | PSNR: 33.73 -> 30.54 | Hurt |
| add warping and symmetry loss terms (ablation) | IM-Net · Vimeo SR | PSNR: 32.07 -> 33.11 | Improved |
| add symmetry loss terms (ablation) | IM-Net with warping terms · Vimeo SR | PSNR: 32.94 -> 33.11 | Improved |
| replace direct motion regression with motion classification (ablation) | IM-Net · Global-shift training experiment | full-resolution fidelity loss | Improved |
| use IM-Net instead of SepConv - Lf | HD inference · HD | run time (msec): 500 -> 30 | Improved |
| use IM-Net instead of TOFlow | FHD inference · FHD | run time (msec): 880 -> 55 | Improved |
Closest papers by meaning
- PhaseNet for Video Frame Interpolation (CVPR 2018 · similarity 0.90)
- MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement (TPAMI 2019 · similarity 0.89)
- Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation (CVPR 2018 · similarity 0.89)
- Channel Attention Is All You Need for Video Frame Interpolation (AAAI 2020 · similarity 0.89)
- Video Frame Interpolation via Adaptive Separable Convolution (ICCV 2017 · similarity 0.88)
- Video Frame Interpolation via Adaptive Convolution (CVPR 2017 · similarity 0.88)
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.
