Research map / Video / Video segmentation and tracking
Event-Based Frame Interpolation With Ad-Hoc Deblurring
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 REFID instead of E2VID+ | blurry frame interpolation · GoPro 11+1 | PSNR: 33.82 -> 35.90 | Helped |
| Use REFID instead of E2VID+ | blurry frame interpolation · HighREV 11+1 | PSNR: 36.36 -> 37.65 | Helped |
| Use REFID instead of Time Lens | sharp frame interpolation · HighREV 7 frames skip | PSNR: 32.81 -> 38.38 | Helped |
| Use REFID instead of EFNet | image deblurring · GoPro | PSNR: 35.46 -> 35.91 | Helped |
| Add multi-scale connections between image and event branches (ablation) | REFID · GoPro 11+1 | PSNR: 33.24 -> 33.61 | Helped |
| Add recurrent event modeling (ablation) | REFID · GoPro 11+1 | PSNR: 33.61 -> 35.36 | Helped |
| Replace ConvLSTM with the EVR block (ablation) | REFID · GoPro 11+1 | PSNR: 34.39 -> 35.81 | Helped |
| Replace ConvGRU with the EVR block (ablation) | REFID · GoPro 11+1 | PSNR: 34.54 -> 35.81 | Helped |
| Add bidirectional instead of unidirectional EVR (ablation) | REFID · GoPro 11+1 | PSNR: 35.36 -> 35.81 | Helped |
| Add EGACA instead of additive fusion (ablation) | REFID · GoPro 11+1 | PSNR: 35.81 -> 36.12 | Helped |
Closest papers by meaning
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.91)
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation (CVPR 2025 · similarity 0.89)
- Latency Correction for Event-guided Deblurring and Frame Interpolation (CVPR 2024 · similarity 0.89)
- Motion-adaptive Transformer for Event-based Image Deblurring (AAAI 2025 · similarity 0.88)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.88)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.88)
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.