Research map / Image generation / Super-resolution
D²R²OSR: Degradation-Disentangled Representation for Real-World Omnidirectional Image Super-Resolution
Hongyu An, Xinfeng Zhang, Xu Fan, 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 a second perspective-based branch alongside ERP (ablation) | ERP baseline · Flickr360 x4 | WS-PSNR: 25.20 -> 25.47 | Improved |
| duplicate the network as a second ERP branch with reduced dims (ablation) | ERP baseline · Flickr360 x4 | WS-PSNR: 25.20 -> 25.35 | Improved |
| replace ERP with perspective representation in a single branch (ablation) | ERP baseline · Flickr360 x4 | WS-PSNR: 25.20 -> 25.09 | Hurt |
| replace OpenCV Remap perspective projection with PPR (ablation) | dual-branch · Flickr360 x4 | WS-PSNR: 25.47 -> 25.50 | Improved |
| PPR resampling vs OpenCV Remap for ERP to perspective (ablation) | projection step · projection fidelity | PSNR: 33.63 -> 38.17 | Improved |
| add DSM in both ERP and PPR branches (ablation) | Baseline_P · Flickr360 x4 | WS-PSNR: 25.50 -> 25.58 | Improved |
| add attention-level injection (ablation) | Baseline_D · Flickr360 x4 | WS-PSNR: 25.58 -> 25.57 | No clear effect |
| add PFAM cross-branch fusion (ablation) | Baseline_D + ALI · Flickr360 x4 | WS-PSNR: 25.57 -> 25.64 | Improved |
| use D2R2OSR vs best baseline AdaIR | real-world ODI-SR · Flickr360 x8 | WS-PSNR: 22.96 -> 23.24 | Improved |
| use D2R2OSR on SUN360 x16 WS-SSIM | real-world ODI-SR · SUN360 x16 | WS-SSIM: AdaIR 0.6185 vs ours 0.6184 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- AdaIR — AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation (ICLR 2025) · better on 9 of 9 shared results
- OSRT — OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer (CVPR 2023) · better on 4 of 4 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
- Omnidirectional Image Super-resolution via Bi-projection Fusion (AAAI 2024 · similarity 0.87)
- Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution (AAAI 2024 · similarity 0.87)
- SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution (ICLR 2024 · similarity 0.86)
- Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · similarity 0.86)
- Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors (AAAI 2025 · similarity 0.86)
- Unsupervised Diffusion-Based Degradation Modeling for Real-World Super-Resolution (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.
