Research map / Video / Video segmentation and tracking
Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Train to predict more intermediate frames jointly (one to seven) (ablation) | Super SloMo · Adobe240-fps | PSNR: 30.26 -> 31.19 | Helped |
| Add flow interpolation refinement (ablation) | Super SloMo · Adobe240-fps | PSNR: 30.34 -> 31.19 | Helped |
| Add visibility maps for occlusion reasoning (ablation) | Super SloMo · Adobe240-fps | PSNR: 31.16 -> 31.19 | No clear effect |
| Add perceptual loss (ablation) | Super SloMo · Adobe240-fps | PSNR: 30.96 -> 31.19 | Helped |
| Add warping loss (ablation) | Super SloMo · Adobe240-fps | PSNR: 30.52 -> 31.19 | Helped |
| Add smoothness loss (ablation) | Super SloMo · Adobe240-fps | PSNR: 31.19 -> 31.19 | No clear effect |
| Train on the full video dataset instead of Adobe240fps only (ablation) | Super SloMo · UCF101 | PSNR: 32.84 -> 33.14 | Helped |
| Use Super SloMo rather than SepConv | video interpolation · UCF101 | PSNR: 33.02 -> 33.14 | Helped |
| Use Super SloMo rather than FlowNet2 | video interpolation · slowflow | IE: 5.35 -> 6.14 | Hurt |
| Use Super SloMo rather than FlowNet2 | video interpolation · high-frame-rate Sintel | PSNR: 30.79 -> 32.38 | Helped |
| Use the multi-frame interpolation setting rather than DVF | unsupervised optical flow · KITTI 2012 | EPE: 14.6 -> 13.0 | Helped |
Closest papers by meaning
- Depth-Aware Video Frame Interpolation (CVPR 2019 · similarity 0.92)
- Context-Aware Synthesis for Video Frame Interpolation (CVPR 2018 · similarity 0.91)
- Video Frame Interpolation via Adaptive Convolution (CVPR 2017 · similarity 0.91)
- Channel Attention Is All You Need for Video Frame Interpolation (AAAI 2020 · similarity 0.91)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.89)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (CVPR 2024 · 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.