Research map / Video / Video segmentation and tracking
A Unified Framework for Event-Based Frame Interpolation With Ad-Hoc Deblurring in the Wild
Lei Sun, Daniel Gehrig, Christos Sakaridis, Mathias Gehrig, Jingyun Liang, Peng Sun, Zhijie Xu, Kaiwei Wang, Luc Van Gool, Davide Scaramuzza
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 multi-scale connection between image and event branches (ablation) | REFID · GoPro blurry frame interpolation (11+1) | PSNR: +0.37 dB | Improved |
| add recurrent EVR block (vs non-recurrent) (ablation) | REFID · GoPro blurry frame interpolation (11+1) | PSNR: +1.75 dB | Improved |
| make EVR block bidirectional (ablation) | REFID · GoPro blurry frame interpolation (11+1) | PSNR: +0.45 dB | Improved |
| use EVR block instead of ConvLSTM/ConvGRU (ablation) | REFID · GoPro blurry frame interpolation (11+1) | PSNR: +0.84 dB | Improved |
| add EGACA event-guided channel attention fusion (ablation) | REFID · GoPro blurry frame interpolation (11+1) | PSNR: +0.31 dB | Improved |
| all components together versus baseline (ablation) | REFID · GoPro blurry frame interpolation (11+1) | PSNR and SSIM: 33.24 -> 36.12 PSNR; 0.950 -> 0.974 SSIM | Improved |
| add blur consistency loss to brightness increment plus warp loss (ablation) | REFID (ssl.) · GoPro self-supervised deblurring | PSNR: 7.22 -> 28.88 | Improved |
| add warp loss to brightness increment and blur consistency (ablation) | REFID (ssl.) · HighREV self-supervised deblurring | PSNR: 27.81 -> 30.04 | Improved |
| add brightness increment loss to blur and warp losses (ablation) | REFID (ssl.) · HighREV self-supervised deblurring | PSNR: 28.53 -> 30.04 | Improved |
| add brightness increment loss to blur and warp losses (ablation) | REFID (ssl.) · GoPro self-supervised deblurring | PSNR: 27.72 -> 28.88 | Improved |
| add images of warped events (IWE) as input (ablation) | REFID (ssl.) · HighREV self-supervised deblurring | PSNR: 30.04 -> 30.94 | Improved |
| use RobustNorm+ instead of RobustNorm voxel normalization (ablation) | REFID (ssl.) · HighREV self-supervised deblurring | PSNR: 28.98 -> 30.04 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- Time Lens — Time Lens: Event-Based Video Frame Interpolation (CVPR 2021) · better on 3 of 3 shared results
- IFRNet — IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation (CVPR 2022) · better on 1 of 1 shared result
- TimeReplayer — TimeReplayer: Unlocking the Potential of Event Cameras for Video Interpolation (CVPR 2022) · 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
- Event-Based Frame Interpolation With Ad-Hoc Deblurring (CVPR 2023 · similarity 0.97)
- Unifying Motion Deblurring and Frame Interpolation With Events (CVPR 2022 · similarity 0.93)
- EVDI++: Event-Based Video Deblurring and Interpolation via Self-Supervised Learning (TPAMI 2026 · similarity 0.92)
- Learning Event-Driven Video Deblurring and Interpolation (ECCV 2020 · similarity 0.91)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.90)
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation (CVPR 2025 · similarity 0.89)
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.
