Research map / Video / Video segmentation and tracking
Blurry Video Frame Interpolation
Check 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 the unified BIN_4 model instead of EDVR + DAIN | Joint deblurring and interpolation · Adobe240 comprehensive | PSNR: 31.52 -> 32.59 | Helped |
| Use the unified BIN_4 model instead of DAIN | Frame interpolation · Adobe240 | PSNR: 31.03 -> 32.51 | Helped |
| Use BIN_4 instead of EDVR for deblurring | Frame deblurring · Adobe240 | PSNR: 32.76 -> 32.67 | Hurt |
| Increase pyramid scale from 2 to 4 (ablation) | BIN · Adobe240 | PSNR: 31.87 -> 32.59 | Helped |
| Increase pyramid scale from 2 to 4 (ablation) | BIN · YouTube240 | PSNR: 34.41 -> 35.10 | Helped |
| Add the inter-pyramid recurrent module (ablation) | BIN_4 · Adobe240 | PSNR: 32.06 -> 32.59 | Helped |
| Add the inter-pyramid recurrent module (ablation) | BIN_4 · YouTube240 | PSNR: 34.72 -> 35.10 | Helped |
| Use ConvLSTM rather than direct previous-frame concatenation (ablation) | BIN_2 · Adobe240 | PSNR: 30.39 -> 31.87 | Helped |
| Use ConvLSTM rather than LSTM (ablation) | BIN_2 · Adobe240 | PSNR: 31.38 -> 31.87 | Helped |
| Use ConvLSTM rather than direct previous-frame concatenation (ablation) | BIN_2 · YouTube240 | PSNR: 33.32 -> 34.41 | Helped |
| Use ConvLSTM rather than LSTM (ablation) | BIN_2 · YouTube240 | PSNR: 34.07 -> 34.41 | Helped |
| Add cycle-consistency loss (ablation) | BIN_4 · Adobe240 | PSNR: 32.42 -> 32.59; 0.17dB gain | Helped |
Closest papers by meaning
- Motion-blurred Video Interpolation and Extrapolation (AAAI 2021 · similarity 0.89)
- Event-Based Frame Interpolation With Ad-Hoc Deblurring (CVPR 2023 · similarity 0.88)
- A Unified Pyramid Recurrent Network for Video Frame Interpolation (CVPR 2023 · similarity 0.87)
- Perception-Oriented Video Frame Interpolation via Asymmetric Blending (CVPR 2024 · similarity 0.84)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.84)
- High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion (AAAI 2025 · similarity 0.84)
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.