Research map / Video / Video segmentation and tracking
Minimum Latency Deep Online Video Stabilization
Zhuofan Zhang, Zhen Liu, Ping Tan, Bing Zeng, Shuaicheng Liu
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 shape-consistency loss to motion-consistency loss (ablation) | online stabilization UNet · NUS dataset | Distortion value: 0.84 -> 0.90 | Improved |
| add shape-consistency loss to motion-consistency loss (ablation) | online stabilization UNet · NUS dataset | Stability score: 0.87 -> 0.86 | No clear effect |
| add scale-preserving loss on top of MC and SC losses (ablation) | online stabilization UNet · NUS dataset | Cropping ratio: 0.85 -> 0.90 | Improved |
| add scale-preserving loss on top of MC and SC losses (ablation) | online stabilization UNet · NUS dataset | Distortion value: 0.90 -> 0.95 | Improved |
| add channel attention to the path smoothing network (ablation) | online stabilization UNet · NUS dataset | Cropping ratio: 0.90 -> 0.92 | Improved |
| add channel attention to the path smoothing network (ablation) | online stabilization UNet · NUS dataset | Stability score: 0.86 -> 0.87 | No clear effect |
| train on MotionStab instead of DeepStab (ablation) | online stabilization UNet and StabNet · NUS dataset | Cropping ratio and distortion value | Improved |
| use deep motion model plus path-smoothing network instead of Meshflow | online video stabilization · NUS dataset (Avg.) | Cropping ratio: 0.7882 -> 0.9242 | Improved |
| use proposed online method instead of Meshflow on stability | online video stabilization · NUS dataset (Avg.) | Stability score: 0.8617 -> 0.8705 | Improved |
| online method versus best offline methods on stability | online video stabilization · NUS dataset (Avg.) | Stability score: 0.9062 -> 0.8705 | Hurt |
Closest papers by meaning
- Minimum Latency Deep Online Video Stabilization and Its Extensions (TPAMI 2024 · similarity 0.98)
- Fast Full-frame Video Stabilization with Iterative Optimization (ICCV 2023 · similarity 0.90)
- 3D Video Stabilization With Depth Estimation by CNN-Based Optimization (CVPR 2021 · similarity 0.89)
- Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance (NeurIPS 2025 · similarity 0.86)
- MotionPro: A Precise Motion Controller for Image-to-Video Generation (CVPR 2025 · similarity 0.85)
- Harnessing Meta-Learning for Improving Full-Frame Video Stabilization (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.
