Research map / Video / Video segmentation and tracking
Deep Bayesian Video Frame Interpolation
Zhiyang Yu, Yu Zhang, Xujie Xiang, Dongqing Zou, Xijun Chen, Jimmy S. Ren
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 image gradient to iteration input (ablation) | Deep Bayesian VFI · GoPro | PSNR: 30.56 -> 31.28 | Improved |
| add flow gradient to iteration input (ablation) | Deep Bayesian VFI · GoPro | PSNR: 31.52 -> 31.53 -> 31.73 with deep reparam; 30.72 -> 30.78 | Improved |
| learn flow updates at each iteration (ablation) | Deep Bayesian VFI · GoPro | PSNR: 31.28 -> 31.52 | Improved |
| add deep reparameterization of flow gradients (16-dim features vs 2-variate Gaussian) (ablation) | Deep Bayesian VFI · GoPro | PSNR: 31.53 -> 31.73 | Improved |
| increase iterations from 1 to 4 (ablation) | Deep Bayesian VFI · GoPro | PSNR: 30.52 -> 31.73 | Improved |
| use Ours instead of FLAVR (8x) | video frame interpolation · GoPro | PSNR: 31.10 -> 31.73 | Improved |
| use Ours instead of XVFI (8x, retrained on X4K1000FPS) | video frame interpolation · X4K1000FPS | PSNR: 30.12 -> 32.89 | Improved |
| use Ours instead of VFIT-B / FLAVR (2x) | video frame interpolation · Vimeo-90K | PSNR: 36.96 -> 36.17 | Hurt |
| use Ours instead of FLAVR (2x) | video frame interpolation · DAVIS | PSNR: 27.44 -> 28.61 | Improved |
Closest papers by meaning
- Depth-Aware Video Frame Interpolation (CVPR 2019 · similarity 0.90)
- Video Frame Interpolation via Adaptive Separable Convolution (ICCV 2017 · similarity 0.90)
- Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation (ICLR 2025 · similarity 0.88)
- EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation (CVPR 2025 · similarity 0.87)
- ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler (ICLR 2025 · similarity 0.87)
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation (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.
