Research map / Video / Video segmentation and tracking
ST-MFNet: A Spatio-Temporal Multi-Flow Network for 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 BLFNet alongside the multi-flow branch (ablation) | ST-MFNet · DAVIS | PSNR: 27.767 -> 28.287 | Helped |
| Add MIFNet alongside the single-flow branch (ablation) | ST-MFNet · VFITex | PSNR: 28.357 -> 29.175 | Helped |
| Add TENet for spatio-temporal texture enhancement (ablation) | ST-MFNet · VFITex | PSNR: 28.241 -> 29.175 | Helped |
| Use UMSResNext instead of U-Net for multi-flow prediction (ablation) | ST-MFNet · DAVIS | PSNR: 28.096 -> 28.287 | Helped |
| Add the up-sampling scale to multi-flow prediction (ablation) | ST-MFNet · VFITex | PSNR: 28.977 -> 29.175 | Helped |
| Fine-tune with ST-GAN perceptual loss rather than Laplacian loss alone (ablation) | ST-MFNet · SNU-FILM Hard | LPIPS: 0.073 -> 0.065 | Helped |
| Fine-tune with ST-GAN perceptual loss rather than Laplacian loss alone (ablation) | ST-MFNet · UCF101 | PSNR: 33.384 -> 33.364 | Hurt |
| Replace ST-MFNet with arithmetic averaging of AdaCoF and Softsplat (ablation) | ST-MFNet · DAVIS | PSNR: 27.361 -> 28.287 | Hurt |
Closest papers by meaning
- FeatureFlow: Robust Video Interpolation via Structure-to-Texture Generation (CVPR 2020 · similarity 0.90)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.90)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 2024 · similarity 0.88)
- VFIMamba: Video Frame Interpolation with State Space Models (NeurIPS 2024 · similarity 0.87)
- Generalizable Implicit Motion Modeling for Video Frame Interpolation (NeurIPS 2024 · similarity 0.87)
- BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions (CVPR 2025 · similarity 0.87)
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.