Research map / Video / Video segmentation and tracking
Learning Cross-Video Neural Representations for High-Quality Frame Interpolation
Wentao Shangguan, Yu Sun, Weijie Gan, Ulugbek S. Kamilov
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 the neural field representation module (vs direct RGB head) (ablation) | CURE · Average over 8 benchmarks | PSNR: 33.32 -> 33.78 | Improved |
| add the neural field representation module (vs direct RGB head) (ablation) | CURE · Average over 8 benchmarks | SSIM: 0.9530 -> 0.9555 | Improved |
| add spatiotemporal coordinate input (ablation) | CURE · Average over 8 benchmarks | PSNR: 33.45 -> 33.78 | Improved |
| add spatiotemporal coordinate input (ablation) | CURE · Average over 8 benchmarks | SSIM: 0.9531 -> 0.9555 | Improved |
| add spatiotemporal coordinate input (ablation) | CURE · Xiph4K | SSIM: 0.9341 -> 0.9389 | Improved |
| add neural representation module (ablation) | CURE · ND Scene | PSNR: 35.13 -> 36.24 | Improved |
| condition neural field on neighbor frames (CURE vs vanilla NF) | CURE · ND Scene Umbrella | PSNR: 23.91 -> 39.66 | Improved |
| condition neural field on neighbor frames (CURE vs NSFF) | CURE · ND Scene Ballon1-2 | PSNR: 24.58 -> 31.05 | Improved |
| CURE vs ABME state-of-the-art | CURE · Vimeo90K | PSNR: 36.18 -> 35.73 | Hurt |
| CURE vs ABME state-of-the-art | CURE · Average over 8 benchmarks | PSNR: 33.35 -> 33.78 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- AdaCoF — AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation (CVPR 2020) · better on 2 of 2 shared results
- BMBC — BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation (ECCV 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation (CVPR 2018 · similarity 0.88)
- Video Frame Interpolation via Adaptive Separable Convolution (ICCV 2017 · similarity 0.88)
- Depth-Aware Video Frame Interpolation (CVPR 2019 · similarity 0.88)
- PhaseNet for Video Frame Interpolation (CVPR 2018 · similarity 0.87)
- A Temporally-Aware Interpolation Network for Video Frame Inpainting (TPAMI 2019 · similarity 0.87)
- EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation (CVPR 2025 · 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.
