Research map / Video / Video segmentation and tracking
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation
Check 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 the joint intermediate-feature and residual design (ablation) | IFRNet · Vimeo90K | PSNR: 34.83 -> 35.51 | Helped |
| Add intermediate feature while omitting residual (ablation) | IFRNet · Vimeo90K | PSNR: 34.83 -> 35.22 | Helped |
| Add residual while omitting intermediate feature (ablation) | IFRNet · Vimeo90K | PSNR: 34.83 -> 35.11 | Helped |
| Add task-oriented flow distillation loss (ablation) | IFRNet · Vimeo90K | PSNR: 35.51 -> 35.72 | Helped |
| Add feature-space geometry consistency loss (ablation) | IFRNet with flow distillation · Vimeo90K | PSNR: 35.72 -> 35.80 | Helped |
| Use fixed-robustness flow distillation with p=0.3 instead of spatially adaptive robustness (ablation) | IFRNet · Vimeo90K | PSNR | Mixed |
| Set fixed flow-distillation robustness near p=1.0 (ablation) | IFRNet · Vimeo90K | PSNR | Hurt |
| Scale IFRNet to the large variant | IFRNet · Vimeo90K | PSNR: 35.80 -> 36.20 | Helped |
| Use IFRNet rather than RIFE | Frame interpolation · Vimeo90K | PSNR: 35.62 -> 35.80 | Helped |
| Use IFRNet rather than ABME | Frame interpolation · SNU-FILM Medium | PSNR: 35.77 -> 35.94 | Helped |
| Use IFRNet rather than ABME | Frame interpolation · SNU-FILM Extreme | PSNR: 25.42 -> 25.05 | Hurt |
| Use IFRNet rather than SoftSplat | Frame interpolation · Middlebury Evaluation | IE: 4.223 -> 4.216 | Helped |
Closest papers by meaning
- Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation (CVPR 2018 · similarity 0.90)
- A Unified Pyramid Recurrent Network for Video Frame Interpolation (CVPR 2023 · similarity 0.89)
- Context-Aware Synthesis for Video Frame Interpolation (CVPR 2018 · similarity 0.89)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.86)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (CVPR 2024 · similarity 0.86)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 2024 · 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.