Research map / Video / Video segmentation and tracking
IAM-VFI : Interpolate Any Motion for Video Frame Interpolation with motion complexity map
Kihwan Yoon, Yong Han Kim, Sungjei Kim, Jinwoo Jeong
Read the paperCheck 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 |
|---|---|---|---|
| train flow network on motion-complexity classified data (easy/medium/hard) (ablation) | RIFE IFNet · Vimeo90K hard | PSNR: 32.131 -> 32.721 | Improved |
| train on hard-classified data but test on easy patches (ablation) | RIFE IFNet · Vimeo90K easy | PSNR: 43.955 -> 43.632 | Hurt |
| average easy/medium/hard frames with fixed 0.33 weights (ablation) | RIFE · HD | PSNR: 32.08 -> 31.97 | Hurt |
| add MCENet motion complexity map to weight frames per region (ablation) | RIFE · Xiph 4K | PSNR: 33.60 -> 33.92 | Improved |
| add complexity loss Lc (ablation) | IAM-VFI on RIFE · Xiph 4K | PSNR: 33.92 -> 34.06 | Improved |
| add Motion Attention Block (MAB) (ablation) | MCENet · Xiph 4K | PSNR: 34.06 -> 34.12 | Improved |
| feed MCM into synthesis network (ablation) | IAM-VFI on RIFE · Xiph 4K | PSNR: 34.12 -> 34.20 | Improved |
| apply IAM-VFI to RIFE | RIFE · UVG | PSNR: 31.13 -> 32.17 | Improved |
| apply IAM-VFI to EMA-VFI | EMA-VFI · UVG | PSNR: 31.19 -> 32.12 | Improved |
| add IAM-VFI (three flow networks plus MCENet) (ablation) | RIFE · 720p runtime | runtime (ms): 48.3ms -> 87.5ms | Hurt |
Closest papers by meaning
- BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions (CVPR 2025 · similarity 0.90)
- IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation (CVPR 2024 · similarity 0.88)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 2024 · similarity 0.88)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.86)
- VFIMamba: Video Frame Interpolation with State Space Models (NeurIPS 2024 · similarity 0.85)
- Generalizable Implicit Motion Modeling for Video Frame Interpolation (NeurIPS 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.
