Research map / Image generation / Super-resolution
LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-Resolution
Xin Deng, Hao Wang, Mai Xu, Yichen Guo, Yuhang Song, Li Yang
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 latitude-adaptive upscaling | ODI super-resolution · ODI-SR 8× | WS-PSNR: 24.29±1.72 -> 24.36±1.73 | Improved |
| use latitude-adaptive upscaling | ODI super-resolution · ODI-SR 16× | WS-PSNR: 21.94± 1.75 -> 22.07± 1.74 | Improved |
| use latitude-adaptive upscaling | ODI super-resolution · SUN 360 Panorama 8× | WS-PSNR: 23.89±2.04 -> 24.02± 2.13 | Improved |
| use latitude-adaptive upscaling | ODI super-resolution · SUN 360 Panorama 16× | WS-PSNR: 21.78±2.12 -> 21.82± 2.36 | Improved |
| increase CA dense block count from 1 to 5 (ablation) | LAU-Net · ODI-SR | WS-PSNR: 23.85dB -> 24.37dB | Improved |
| increase evaluator count from K=4 to K=12 (ablation) | LAU-Net · ODI-SR | WS-PSNR: 22.64 -> 24.36 | Improved |
| use latitude-adaptive loss instead of L1 loss (ablation) | LAU-Net · ODI-SR | WS-PSNR: 24.31 -> 24.36 | Improved |
| use latitude-adaptive loss instead of L2 loss (ablation) | LAU-Net · ODI-SR | WS-PSNR: 24.28 -> 24.36 | Improved |
Later papers that compared with this method
3 later accepted papers report LAU-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors (AAAI 2025 · better on 0 of 1 shared result)
- OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution (ICCV 2023 · better on 1 of 2 shared results)
- SphereSR: 360deg Image Super-Resolution With Arbitrary Projection via Continuous Spherical Image Representation (CVPR 2022 · 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
- OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model (ECCV 2024 · similarity 0.87)
- Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors (AAAI 2025 · similarity 0.86)
- Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution (AAAI 2024 · similarity 0.85)
- Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning (CVPR 2025 · similarity 0.85)
- Towards Realistic Data Generation for Real-World Super-Resolution (ICLR 2025 · similarity 0.85)
- Block-Based Multi-Scale Image Rescaling (AAAI 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.
