Research map / Video / Video segmentation and tracking
Event-Based Blurry Frame Interpolation Under Blind Exposure
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 |
|---|---|---|---|
| Estimate exposure duty using the proposed event-assisted method rather than fixing exposure prior (ablation) | Blurry frame interpolation under blind exposure · RealSharp-DAVIS | PSNR | Helped |
| Add events to RGB for exposure estimation (ablation) | Exposure estimation module · RealSharp-DAVIS | PSNR: 28.420 -> 29.529 | Helped |
| Add the Laplacian blurry-level input (ablation) | Exposure estimation module · RealSharp-DAVIS | PSNR: 29.529 -> 29.944 | Helped |
| Add the dark-channel blurry-level input (ablation) | Exposure estimation module · RealSharp-DAVIS | PSNR: 29.944 -> 30.185 | Helped |
| Use dual-path rather than single-path temporal-exposure control (ablation) | Temporal-exposure control · RealSharp-DAVIS | PSNR: 30.185 -> 30.675 | Helped |
| Add KPN-based revised modulation (ablation) | Sharp-frame reconstruction · RealSharp-DAVIS | PSNR: 30.675 -> 30.759 | Helped |
| Add the detail restoration network (ablation) | Sharp-frame reconstruction · RealSharp-DAVIS | PSNR: 30.759 -> 31.378 | Helped |
| Use stage-wise training rather than end-to-end training (ablation) | Proposed method · RealSharp-DAVIS | PSNR: 31.378 -> 31.913 | Helped |
| Use the proposed method instead of LEDVDI | Blurry frame interpolation under blind exposure · GoPro, train-test consistency | PSNR (dB): 27.60 -> 28.46 | Helped |
| Use the proposed method instead of LEDVDI | Blurry frame interpolation under blind exposure · RealSharp-DAVIS, train-test consistency | PSNR (dB): 30.12 -> 31.89 | Helped |
| Use the proposed method instead of EVDI | Blurry frame interpolation under blind exposure · RealSharp-DAVIS, train-test inconsistency | PSNR (dB): 28.51 -> 31.27 | Helped |
Closest papers by meaning
- Event-Based Frame Interpolation With Ad-Hoc Deblurring (CVPR 2023 · similarity 0.91)
- Frequency-aware Event-based Video Deblurring for Real-World Motion Blur (CVPR 2024 · similarity 0.88)
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation (CVPR 2025 · similarity 0.87)
- Latency Correction for Event-guided Deblurring and Frame Interpolation (CVPR 2024 · similarity 0.86)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.86)
- TTA-EVF: Test-Time Adaptation for Event-based Video Frame Interpolation via Reliable Pixel and Sample Estimation (CVPR 2024 · similarity 0.85)
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.