Research map / Video / Video segmentation and tracking
Video Frame Interpolation via Deformable Separable Convolution
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 |
|---|---|---|---|
| add learned deformable offsets and masks to separable kernels (5x5 instead of 51) | SepConv-L1 · Vimeo90K | PSNR: 33.79 -> 34.73 | Helped |
| add deformable offsets and masks | SepConv-L1 · UCF101 | PSNR: 34.78 -> 35.08 | Helped |
| add mask estimator (ablation) | DSepConv 5x5 · Vimeo90K | PSNR: 34.55 -> 34.73 | Helped |
| add mask estimator (ablation) | DSepConv 5x5 · Middlebury Other | IE: 2.11 -> 2.06 | Helped |
| increase kernel size from 1x1 to 5x5 (ablation) | DSepConv · Vimeo90K | PSNR: 33.63 -> 34.73 | Helped |
| increase kernel size from 3x3 to 5x5 (ablation) | DSepConv · UCF101 | PSNR: 34.79 -> 35.08 | Helped |
| DSepConv vs DAIN (no flow/depth sub-networks) | frame interpolation · Middlebury Evaluation | average IE: 4.86 vs 4.86 | No clear effect |
Closest papers by meaning
- Video Frame Interpolation via Adaptive Convolution (CVPR 2017 · similarity 0.91)
- Depth-Aware Video Frame Interpolation (CVPR 2019 · similarity 0.89)
- AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation (CVPR 2020 · similarity 0.88)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.86)
- Perception-Oriented Video Frame Interpolation via Asymmetric Blending (CVPR 2024 · similarity 0.85)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 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.