Research map / Image generation / Super-resolution
Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation
Shaolin Wang, Yuying Li, Lei Zhong, Shigang Li, Jianfeng Li
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 spherical rotation-translation augmentation (ablation) | EAM · ODI-SR x8 | WS-PSNR: 24.70 -> 25.69 | Improved |
| add spherical rotation-translation augmentation (ablation) | EAM · ODI-SR x8 | WS-SSIM: 0.6529 -> 0.6839 | Improved |
| add spherical augmentation (ablation) | EAM · ODI-SR x16 | WS-PSNR: 23.10 -> 23.86 | Improved |
| add Edge Enhanced Block (ablation) | EAM · ODI-SR x8 | WS-PSNR: 25.17 -> 25.69 | Improved |
| add Edge Refined Block (ablation) | EAM · ODI-SR x8 | WS-PSNR: 25.17 -> 25.69 | Improved |
| add Global Integration Block (ablation) | EAM · ODI-SR x8 | WS-PSNR: 24.95 -> 25.69 | Improved |
| add SSIM loss (ablation) | EAM · ODI-SR x8 | WS-PSNR: 25.29 -> 25.69 | Improved |
| add perceptual loss (ablation) | EAM · ODI-SR x8 | WS-SSIM: 0.6690 -> 0.6839 | Improved |
| compare EAM with LAPR on structure | EAM · ODI-SR x8 | WS-SSIM: 0.6839 (EAM) vs 0.6886 (LAPR) | Mixed |
| use EAM instead of LAPR for x16 | EAM · ODI-SR x16 | time: 0.312 s -> 0.022 s | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- OSRT — OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer (CVPR 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors (AAAI 2025 · similarity 0.90)
- Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution (AAAI 2024 · similarity 0.88)
- Omnidirectional Image Super-resolution via Bi-projection Fusion (AAAI 2024 · similarity 0.85)
- ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings (NeurIPS 2024 · similarity 0.85)
- Occlusion-Embedded Hybrid Transformer for Light Field Super-Resolution (AAAI 2025 · similarity 0.85)
- Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning (CVPR 2025 · similarity 0.84)
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.
