Research map / Video / Video segmentation and tracking
A Flexible Recurrent Residual Pyramid Network for Video Frame Interpolation
Haoxian Zhang, Yang Zhao, Ronggang Wang
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 |
|---|---|---|---|
| increase pyramid layers from 1 to 4 (ablation) | RRPN w/o refinement · Thumos15 (720P) | PSNR: 33.56 -> 34.69 | Improved |
| increase pyramid layers from 1 to 2 (ablation) | RRPN w/o refinement · Our test set (480P) | PSNR: 30.74 -> 31.75 | Improved |
| increase pyramid layers from 2 to 3 (ablation) | RRPN w/o refinement · Our test set (480P) | PSNR: 31.75 -> 31.80 | No clear effect |
| increase pyramid layers from 1 to 2 (ablation) | RRPN w/o refinement · UCF101 (240P) | PSNR: 34.64 -> 34.72 | No clear effect |
| increase pyramid layers from 2 to 3 (ablation) | RRPN w/o refinement · Thumos15 (720P) | PSNR: 34.50 -> 34.65 | Improved |
| add full refinement network (ablation) | RRPN-L2 · Our test set (480P) | PSNR: 31.75 -> 31.90 | Improved |
| add context maps to refinement network (edge R to whole R) (ablation) | RRPN-L2 · Our test set (480P) | PSNR: 31.83 -> 31.90 | Improved |
| add edge maps to refinement network (context R to whole R) (ablation) | RRPN-L2 · Our test set (480P) | PSNR: 31.86 -> 31.90 | Improved |
| add refinement network (basic R, no context or edge maps) (ablation) | RRPN-L2 · Our test set (480P) | SSIM: 0.913 -> 0.910 | Hurt |
| use more pyramid layers (RRPN-L5) for 4K (ablation) | RRPN · H.266 4K | PSNR: 34.86 -> 35.28 | Improved |
| use four layers instead of three for 1080P (ablation) | RRPN · ActivityNet (1080P) | PSNR: 30.13 -> 30.08 | Mixed |
| remove refinement network to cut cost | RRPN-L2 · 480P efficiency | runtime (s): 0.12 -> 0.06 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MEMC-Net — MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement (TPAMI 2019) · better on 6 of 6 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
- A Unified Pyramid Recurrent Network for Video Frame Interpolation (CVPR 2023 · similarity 0.91)
- UPR-Net: A Unified Pyramid Recurrent Network for Video Frame Interpolation (IJCV 2024 · similarity 0.91)
- Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation (CVPR 2018 · similarity 0.89)
- Depth-Aware Video Frame Interpolation (CVPR 2019 · similarity 0.88)
- Context-Aware Synthesis for Video Frame Interpolation (CVPR 2018 · similarity 0.88)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (CVPR 2024 · 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.
