Research map / Video / Video segmentation and tracking
Exploring Discontinuity for Video Frame 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 VFIT-B with FTM augmentation (ablation) | VFIT-B · GDM | PSNR: 30.019 -> 30.473 | Helped |
| Train AdaCoF with FTM augmentation (ablation) | AdaCoF · GDM | PSNR: 29.980 -> 30.064 | Helped |
| Add D-map with two input frames (ablation) | AdaCoF · GDM | PSNR: 29.980 -> 30.097 | Helped |
| Add D-map with two input frames (ablation) | CAIN · GDM | PSNR: 30.238 -> 30.616 | Helped |
| Add D-map and use four input frames (ablation) | CAIN · Vimeo-90k | PSNR: 34.699 -> 35.540 | Helped |
| Add D-map with two input frames (ablation) | CAIN · Vimeo-90k | PSNR: 34.699 -> 34.546 | Hurt |
| Add D-map with two input frames (ablation) | AdaCoF · Vimeo-90k | PSNR: 34.103 -> 34.385 | Helped |
| Add L_D supervision to AdaCoF-D (4) (ablation) | AdaCoF · GDM | PSNR: 30.212 -> 30.242 | Helped |
| Add L_D supervision to CAIN-D (4) (ablation) | CAIN · GDM | PSNR: 31.011 -> 30.936 | Hurt |
| Add L_D supervision to VFIT-B-D (4) (ablation) | VFIT-B · GDM | LPIPS: 0.0652 -> 0.0645 | Helped |
| Add D-map and L_D to VFIT-B with four input frames (ablation) | VFIT-B · Vimeo-90k | PSNR: 36.743 -> 36.671 | Hurt |
| Add D-map and L_D to VFIT-B with four input frames (ablation) | VFIT-B · GDM | PSNR: 30.019 -> 30.921 | Helped |
Closest papers by meaning
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.88)
- Perception-Oriented Video Frame Interpolation via Asymmetric Blending (CVPR 2024 · similarity 0.87)
- VFIMamba: Video Frame Interpolation with State Space Models (NeurIPS 2024 · similarity 0.87)
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation (CVPR 2025 · similarity 0.86)
- BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions (CVPR 2025 · similarity 0.86)
- LDMVFI: Video Frame Interpolation with Latent Diffusion Models (AAAI 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.