Research map / Video / Video segmentation and tracking
Scene-Adaptive Video Frame Interpolation via Meta-Learning
Myungsub Choi, Janghoon Choi, Sungyong Baik, Tae Hyun Kim, Kyoung Mu Lee
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 |
|---|---|---|---|
| meta-train the DVF initialization for one-step test-time scene adaptation | DVF · VimeoSeptuplet | PSNR (dB): 32.21 -> 32.27 | Improved |
| meta-train DVF for test-time scene adaptation | DVF · Middlebury-OTHERS | PSNR (dB): 29.51 -> 29.70 | Improved |
| meta-train SuperSloMo for test-time scene adaptation | SuperSloMo · VimeoSeptuplet | PSNR (dB): 32.76 -> 33.12 | Improved |
| meta-train SuperSloMo for test-time scene adaptation | SuperSloMo · Middlebury-OTHERS | PSNR (dB): 33.54 -> 33.70 | Improved |
| meta-train SuperSloMo for test-time scene adaptation | SuperSloMo · HD | PSNR (dB): 29.66 -> 29.81 | Improved |
| meta-train SepConv for test-time scene adaptation | SepConv · VimeoSeptuplet | PSNR (dB): 33.72 -> 34.17 | Improved |
| meta-train SepConv for test-time scene adaptation | SepConv · Middlebury-OTHERS | PSNR (dB): 35.14 -> 35.81 | Improved |
| meta-train SepConv for test-time scene adaptation | SepConv · HD | PSNR (dB): 30.04 -> 30.19 | Improved |
| meta-train DAIN for test-time scene adaptation | DAIN · VimeoSeptuplet | PSNR (dB): 34.86 -> 34.94 | Improved |
| meta-train DAIN for test-time scene adaptation | DAIN · Middlebury-OTHERS | PSNR (dB): 36.57 -> 36.50 | Hurt |
| meta-train DAIN for test-time scene adaptation | DAIN · HD | PSNR (dB): 30.45 -> 30.51 | Improved |
| use one rather than zero test-time updates with the meta-trained model (ablation) | Meta-trained SepConv · Middlebury-OTHERS | PSNR (dB): 34.90 -> 35.81 | Improved |
Closest papers by meaning
- Test-Time Adaptation for Video Frame Interpolation via Meta-Learning (TPAMI 2021 · similarity 0.97)
- Deep Bayesian Video Frame Interpolation (ECCV 2022 · similarity 0.88)
- Harnessing Meta-Learning for Improving Full-Frame Video Stabilization (CVPR 2024 · similarity 0.88)
- EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation (CVPR 2025 · similarity 0.87)
- Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation (ICLR 2025 · similarity 0.87)
- Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation (CVPR 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.
