Research map / Video / Video segmentation and tracking
SVFI: Spiking-Based Video Frame Interpolation for High-Speed Motion
Lujie Xia, Jing Zhao, Ruiqin Xiong, Tiejun Huang
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 spike-stream input to RGB-frame interpolation (ablation) | SVFI · GoPro test dataset | PSNR: 24.84 -> 34.66 | Improved |
| use the feature fusion module instead of simple concatenation and convolution layers (ablation) | SVFI · GoPro test dataset | PSNR: 33.60 -> 34.66 | Improved |
| use spike streams alongside RGB frames | SVFI · Middlebury, 1 frame skip | PSNR: 31.08 -> 33.87 | Improved |
| use spike streams alongside RGB frames | SVFI · Middlebury, 3 frames skip | PSNR: 27.18 -> 31.29 | Improved |
| use spike streams alongside RGB frames | SVFI · Vimeo90k, 1 frame skip | PSNR: 34.90 -> 37.78 | Improved |
| use spike streams alongside RGB frames | SVFI · GoPro, 7 frames skip | PSNR: 29.08 -> 34.66 | Improved |
| use spike streams alongside RGB frames | SVFI · GoPro, 15 frames skip | PSNR: 24.39 -> 30.97 | Improved |
| use spike streams alongside RGB frames | SVFI · HS-ERGB, 5 frames skip | PSNR: 33.13 -> 33.98 | Improved |
| use spike streams alongside RGB frames | SVFI · HS-ERGB, 7 frames skip | PSNR: 32.31 -> 32.84 | 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.
- Time Lens — Time Lens: Event-Based Video Frame Interpolation (CVPR 2021) · better on 2 of 2 shared results
- BMBC — BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation (ECCV 2020) · better on 1 of 1 shared result
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
- Perception-Oriented Video Frame Interpolation via Asymmetric Blending (CVPR 2024 · similarity 0.87)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.87)
- Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras (NeurIPS 2024 · similarity 0.87)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 2024 · similarity 0.86)
- Spk2SRImgNet: Super-Resolve Dynamic Scene from Spike Stream via Motion Aligned Collaborative Filtering (CVPR 2025 · similarity 0.86)
- BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions (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.
