Research map / Video / Video segmentation and tracking
Spatio-Temporal Distortion Aware Omnidirectional Video Super-Resolution
Hongyu An, Xinfeng Zhang, Shijie Zhao, Li Zhang, Ruiqin Xiong
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 latitude distortion map loss (ablation) | baseline · ODV-SR dataset x4 | WS-PSNR: 29.83 -> 29.93 | Improved |
| add saliency attention map loss (ablation) | baseline · ODV-SR dataset x4 | WS-PSNR: 29.83 -> 29.91 | Improved |
| add spatio distortion alignment (ablation) | baseline · ODV-SR dataset x4 | WS-PSNR: 29.83 -> 29.85 | Mixed |
| add cylinder position encoding (ablation) | baseline · ODV-SR dataset x4 | WS-PSNR: 29.85 -> 29.88 | Mixed |
| add interlaced multi-frame reconstruction (ablation) | baseline · ODV-SR dataset x4 | WS-PSNR: 29.83 -> 30.06 | Improved |
| add interlaced multi-frame fusion (ablation) | baseline · ODV-SR dataset x4 | WS-PSNR: 30.06 -> 30.02 | Improved |
| add data augmentation (new ODV-SR dataset) (ablation) | baseline · ODV-SR dataset x4 | WS-PSNR: 30.02 -> 30.04 | Mixed |
| set fusion weights alpha1,beta1 to 0.01 instead of 0 (ablation) | IMFR · ODV-SR dataset x4 | WS-PSNR: 29.83 -> 30.02 | Improved |
| set fusion weights alpha1,beta1 to 0.1 instead of 0.01 (ablation) | IMFR · ODV-SR dataset x4 | WS-PSNR: 30.02 -> 29.69 | Hurt |
| set LSA weights alpha2,beta2 to 1 instead of 0.1 (ablation) | LSA loss · ODV-SR dataset x4 | WS-PSNR: 29.93 -> 29.81 | Hurt |
| use STDAN instead of IA-RT | STDAN · ODV-SR dataset x4 | WS-PSNR: 30.18 -> 30.23 | Improved |
| use STDAN instead of IA-RT on MiG | STDAN · ODV-SR dataset x4 | PSNR: 31.24 -> 31.21 | No clear effect |
Closest papers by meaning
- SpatioTemporal Difference Network for Video Depth Super-Resolution (AAAI 2026 · similarity 0.88)
- D²R²OSR: Degradation-Disentangled Representation for Real-World Omnidirectional Image Super-Resolution (ECCV 2026 · similarity 0.88)
- Space-Time-Aware Multi-Resolution Video Enhancement (CVPR 2020 · similarity 0.87)
- Time Without Time: Pseudo-Temporal Representation for Space-Time Super-Resolution (CVPR 2026 · similarity 0.87)
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · similarity 0.86)
- VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · 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.
