Research map / Video / Video segmentation and tracking
Out-of-Boundary View Synthesis Towards Full-Frame Video Stabilization
Yufei Xu, Jing Zhang, Dacheng Tao
Read the paperCheck 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 |
|---|---|---|---|
| add OVS to DUT | DUT · NUS | cropping ratio: 0.867 -> 0.967 | Improved |
| add OVS to PWStabNet | DUT · NUS | cropping ratio: 0.877 -> 0.959 | Improved |
| add OVS to Yu et al. | DUT · NUS | cropping ratio: 0.827 -> 0.922 | Improved |
| add OVS to StabNet | DUT · NUS | cropping ratio: 0.676 -> 0.763 | Improved |
| add OVS to MeshFlow | DUT · NUS | cropping ratio: 0.770 -> 0.898 | Improved |
| add OVS to MeshFlow | DUT · NUS | distortion: 0.673 -> 0.683 | No clear effect |
| add OVS to DUT | DUT · NUS | stability: 0.845 -> 0.847 | No clear effect |
| fill remaining holes with nearest neighbor interpolation (OVS*) | DUT · NUS | cropping ratio: 0.967 -> 0.999 | Improved |
| use full two-stage OVS instead of coarse alignment only (ablation) | DUT · DeepStab val | PSNR: 17.66 -> 22.84 | Improved |
| add coarse alignment to fine-only alignment (ablation) | DUT · DUT with aligned frames | cropping ratio: 0.868 -> 0.967 | Improved |
| add fine alignment to coarse alignment (ablation) | DUT · DeepStab val | SSIM: 0.61 -> 0.82 | Improved |
| add fine alignment to coarse alignment for stabilization (ablation) | DUT · DUT | stability: 0.848 -> 0.847 | No clear effect |
Closest papers by meaning
- Fast Full-frame Video Stabilization with Iterative Optimization (ICCV 2023 · similarity 0.87)
- 3D Multi-frame Fusion for Video Stabilization (CVPR 2024 · similarity 0.84)
- Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion (NeurIPS 2025 · similarity 0.84)
- OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation (CVPR 2024 · similarity 0.83)
- Harnessing Meta-Learning for Improving Full-Frame Video Stabilization (CVPR 2024 · similarity 0.83)
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis (CVPR 2024 · similarity 0.83)
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.
