Research map / Image generation / Super-resolution
SphereSR: 360deg Image Super-Resolution With Arbitrary Projection via Continuous Spherical Image Representation
Youngho Yoon, Inchul Chung, Lin Wang, Kuk-Jin Yoon
Check 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 |
|---|---|---|---|
| use SphereSR instead of LAU-Net | ERP super-resolution · ODI-SR ×16 ERP | WS-PSNR: 22.07 -> 22.51 | Improved |
| use SphereSR instead of LAU-Net | ERP super-resolution · SUN 360 Panorama ×16 ERP | WS-SSIM: 0.5824 -> 0.6342 | Improved |
| use SphereSR instead of LAU-Net | arbitrary-projection super-resolution · ODI-SR perspective FOV 90 | PSNR: 26.39 -> 26.76 | Improved |
| add GA-Conv rather than SpherePHD-style rotated kernel weight sharing (ablation) | SphereSR feature extraction · ODI-SR ×8 ERP | WS-PSNR: 24.20 -> 24.34 | Improved |
| add GA-Conv rather than SpherePHD-style rotated kernel weight sharing (ablation) | SphereSR feature extraction · SUN 360 Panorama ×8 ERP | WS-PSNR: 23.98 -> 24.10 | Improved |
| add SLIIF instead of pixel-shuffle subdivision (ablation) | SphereSR · ODI-SR ×8 ERP | WS-PSNR: 24.31 -> 24.34 | Improved |
| add feature loss (ablation) | SphereSR · ODI-SR ×8 ERP | WS-PSNR: 24.34 -> 24.37 | Improved |
| add feature loss (ablation) | SphereSR · ODI-SR ×16 ERP | WS-PSNR: 22.47 -> 22.51 | Improved |
| add SLIIF (ablation) | SphereSR · ODI-SR perspective FOV 90 | PSNR: 26.66 -> 26.76 | Improved |
| add SLIIF (ablation) | SphereSR · SUN 360 Panorama perspective FOV 90 | PSNR: 24.83 -> 24.97 | Improved |
| use the proposed data structure instead of SpherePHD's neighbor-stacking structure (ablation) | spherical CNN feature extraction · activation memory, level 6 | activation memory (MB): 6714 -> 2138 | Improved |
Later papers that compared with this method
3 later accepted papers report SphereSR as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution (AAAI 2024 · better on 1 of 1 shared result)
- OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer (CVPR 2023 · better on 4 of 4 shared results)
- OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution (ICCV 2023 · better on 1 of 1 shared result)
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.
- LAU-Net — LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-Resolution (CVPR 2021) · better on 10 of 11 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
- Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution (AAAI 2024 · similarity 0.88)
- Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors (AAAI 2025 · similarity 0.86)
- Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera (CVPR 2026 · similarity 0.86)
- SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception (CVPR 2025 · similarity 0.85)
- SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model (AAAI 2024 · similarity 0.83)
- SGCR: Spherical Gaussians for Efficient 3D Curve Reconstruction (CVPR 2025 · 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.
