Research map / Video / Video segmentation and tracking
TimeReplayer: Unlocking the Potential of Event Cameras for Video Interpolation
Weihua He, Kaichao You, Zhendong Qiao, Xu Jia, Ziyang Zhang, Wenhui Wang, Huchuan Lu, Yaoyuan Wang, Jianxing Liao
Check 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 |
|---|---|---|---|
| Use event streams with frames and unsupervised cycle-consistent training instead of frame-only unsupervised interpolation | TimeReplayer · GoPro 7 skip (whole) | PSNR: 28.23 -> 34.02 | Improved |
| Use event streams with frames and unsupervised cycle-consistent training instead of frame-only unsupervised interpolation | TimeReplayer · Middlebury (other) 3 skip | PSNR: 24.86 -> 30.91 | Improved |
| Use event streams with frames and unsupervised cycle-consistent training instead of frame-only unsupervised interpolation | TimeReplayer · Vimeo90k (interpolation) 1 skip | PSNR: 30.38 -> 35.12 | Improved |
| Use TimeReplayer rather than Time Lens | Video interpolation with real events · HQF 1 skip | PSNR: 32.49 -> 31.07 | Hurt |
| Use TimeReplayer rather than Time Lens | Video interpolation with real events · HS-ERGB far 7 skip | PSNR: 32.31 -> 30.07 | Hurt |
| Use TimeReplayer rather than Time Lens | Video interpolation with real events · HS-ERGB close 5 skip | PSNR: 32.19 -> 31.21 | Hurt |
| Use separate forward and backward event flow estimators instead of a shared estimator (ablation) | TimeReplayer · GoPro 7 skip | PSNR: 33.78 -> 34.02 | Improved |
| Estimate intermediate flows directly rather than proportionally from input-frame flow (ablation) | TimeReplayer · GoPro 7 skip | PSNR: 32.05 -> 34.02 | Improved |
| Use the proposed event-based model rather than UnSuperSloMo with concatenated event input (ablation) | TimeReplayer · GoPro 7 skip | PSNR: 32.16 -> 34.02 | Improved |
| Fine-tune on additional unsupervised DDD17 event data | TimeReplayer · HQF 3 skip | PSNR: +2.72 | Improved |
| Fine-tune on additional unsupervised DDD17 event data | TimeReplayer · HQF 1 skip | PSNR: +2.86 | Improved |
Later papers that compared with this method
1 later accepted paper reports TimeReplayer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- A Unified Framework for Event-Based Frame Interpolation With Ad-Hoc Deblurring in the Wild (TPAMI 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Time Lens — Time Lens: Event-Based Video Frame Interpolation (CVPR 2021) · better on 0 of 13 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
- Time Lens: Event-Based Video Frame Interpolation (CVPR 2021 · similarity 0.92)
- Latency Correction for Event-guided Deblurring and Frame Interpolation (CVPR 2024 · similarity 0.88)
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025 · similarity 0.87)
- TimeTracker: Event-based Continuous Point Tracking for Video Frame Interpolation with Non-linear Motion (CVPR 2025 · similarity 0.87)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.87)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 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.
