Research map / Video / Video segmentation and tracking
All at Once: Temporally Adaptive Multi-Frame Interpolation with Advanced Motion Modeling
Zhixiang Chi, Rasoul Mohammadi Nasiri, Zheng Liu, Juwei Lu, Jin Tang, Konstantinos N Plataniotis
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 |
|---|---|---|---|
| add post processing (ablation) | Ours · Adobe240 | PSNR: 33.87 -> 34.37 | Improved |
| add adversarial loss (ablation) | Ours · Adobe240 | PSNR: 34.35 -> 34.37 | Improved |
| add adversarial loss (ablation) | Ours · Adobe240 | TCC: 0.850 -> 0.860 | Improved |
| add second-stage optical flow (ablation) | Ours · Adobe240 | PSNR: 34.24 -> 34.37 | Improved |
| add optical flow relaxation loss (ablation) | Ours · Adobe240 | PSNR: 33.92 -> 34.37 | Improved |
| add optical flow relaxation loss (ablation) | Ours · GOPRO | PSNR: 32.45 -> 32.91 | Improved |
| add temporal pyramid (ablation) | Ours · Adobe240 | PSNR: 33.92 -> 34.37 | Improved |
| add temporal pyramid (ablation) | Ours · GOPRO | PSNR: 32.37 -> 32.91 | Improved |
| use cubic instead of linear motion model (ablation) | Ours · Adobe240 | PSNR: 33.97 -> 34.37 | Improved |
| use cubic instead of quadratic motion model (ablation) | Ours · GOPRO | PSNR: 32.70 -> 32.91 | Improved |
| generate 7 frames instead of 1 frame (ablation) | Ours · Vimeo90K | PSNR: 32.02 -> 34.93 | Improved |
| generate 7 frames instead of 1 frame (ablation) | Ours · DAVIS | PSNR: 27.07 -> 27.91 | Improved |
Closest papers by meaning
- Video Frame Interpolation without Temporal Priors (NeurIPS 2020 · similarity 0.90)
- Realtime Video Frame Interpolation using One-Step Diffusion Sampling (ICLR 2026 · similarity 0.89)
- Video Frame Interpolation With Many-to-Many Splatting and Spatial Selective Refinement (TPAMI 2023 · similarity 0.88)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.88)
- EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation (CVPR 2025 · similarity 0.87)
- Framer: Interactive Frame Interpolation (ICLR 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.
