Research map / Video / Video segmentation and tracking
Depth-Aware 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 depth-aware flow projection with pretrained depth jointly optimized (ablation) | DAIN · UCF101 | PSNR: 34.91 -> 34.99 | Helped |
| use depth-aware flow projection with pretrained depth jointly optimized (ablation) | DAIN · Vimeo90K | PSNR: 34.47 -> 34.71 | Helped |
| initialize depth estimation from scratch instead of using pretrained depth (ablation) | DAIN · UCF101 | PSNR: 34.91 -> 34.85 | Hurt |
| initialize depth estimation from scratch instead of using pretrained depth (ablation) | DAIN · Vimeo90K | PSNR: 34.47 -> 34.30 | Hurt |
| add pretrained depth initialization to flow projection (ablation) | DAIN · Vimeo90K | PSNR: 34.47 -> 34.52 | Helped |
| add depth maps as contextual features (ablation) | DAIN · UCF101 | PSNR: 34.84 -> 34.90 | Helped |
| add pretrained conv1 features and depth maps as context (ablation) | DAIN · UCF101 | PSNR: 34.84 -> 34.97 | Helped |
| use learned hierarchical features rather than pretrained conv1 features, with depth maps (ablation) | DAIN · Vimeo90K | PSNR: 34.49 -> 34.71 | Helped |
| add learned hierarchical contextual features and depth maps (ablation) | DAIN · Middlebury Other | IE: 2.21 -> 2.04 | Helped |
| use DAIN instead of MEMC-Net | video frame interpolation · Vimeo90K | PSNR: 34.29 -> 34.71 | Helped |
Closest papers by meaning
- Context-Aware Synthesis for Video Frame Interpolation (CVPR 2018 · similarity 0.94)
- Channel Attention Is All You Need for Video Frame Interpolation (AAAI 2020 · similarity 0.93)
- Explicit Depth-Aware Blurry Video Frame Interpolation Guided by Differential Curves (CVPR 2025 · similarity 0.88)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (CVPR 2024 · similarity 0.88)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.88)
- Sparse Global Matching for Video Frame Interpolation with Large Motion (CVPR 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.