Research map / Video / Video segmentation and tracking
Spatiotemporal Deformation Perception for Fisheye Video Rectification
Shangrong Yang, Chunyu Lin, Kang Liao, Yao Zhao
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 the Flow Enhancement Network to the Flow Estimation Network (ablation) | Spatiotemporal Deformation Perception method · Youtube-VOS test | PSNR: 21.23 -> 28.18 | Improved |
| Add the Flow Enhancement Network to the Flow Estimation Network (ablation) | Spatiotemporal Deformation Perception method · Youtube-VOS test | Stability: 0.865 -> 0.895 | Improved |
| Add Temporal Weighting Scheme (ablation) | Spatiotemporal Deformation Perception method · Youtube-VOS test | Stability: 0.884 -> 0.895 | Improved |
| Add Temporal Weighting Scheme (ablation) | Spatiotemporal Deformation Perception method · Youtube-VOS test | PSNR: 26.98 -> 28.18 | Improved |
| Add Temporal Deformation Aggregator (ablation) | Spatiotemporal Deformation Perception method · Youtube-VOS test | PSNR: 27.54 -> 28.18 | Improved |
| Add Temporal Deformation Aggregator (ablation) | Spatiotemporal Deformation Perception method · Youtube-VOS test | Stability: 0.892 -> 0.895 | No clear effect |
| Add Spatial Deformation Perception (ablation) | Spatiotemporal Deformation Perception method · Youtube-VOS test | PSNR: 27.03 -> 28.18 | Improved |
| Add Spatial Deformation Perception (ablation) | Spatiotemporal Deformation Perception method · Youtube-VOS test | Stability: 0.891 -> 0.895 | No clear effect |
| Use the proposed video correction method instead of DDM | Fisheye video correction · DAVIS test | PSNR: 24.90 -> 25.92 | Improved |
| Use the proposed video correction method instead of DDM | Fisheye video correction · Youtube-VOS test | PSNR: 26.42 -> 28.18 | Improved |
Closest papers by meaning
- Progressively Complementary Network for Fisheye Image Rectification Using Appearance Flow (CVPR 2021 · similarity 0.86)
- SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning (ICCV 2023 · similarity 0.86)
- Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow (CVPR 2025 · similarity 0.83)
- StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences (NeurIPS 2024 · similarity 0.83)
- HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene (NeurIPS 2025 · similarity 0.82)
- VideoSPatS: Video SPatiotemporal Splines for Disentangled Occlusion, Appearance and Motion Modeling and Editing (CVPR 2025 · similarity 0.82)
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.
