Research map / Image generation / Super-resolution
Guided Super-Resolution As Pixel-to-Pixel Transformation
Riccardo de Lutio, Stefano D'Aronco, Jan Dirk Wegner, Konrad Schindler
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 |
|---|---|---|---|
| use pixel-to-pixel guide-to-source mapping instead of bicubic upsampling | guided SR · Depth map SR (x32) | MSE (pixel^2): 54.1 -> 26.0 | Improved |
| use pixel-to-pixel mapping instead of the SD filter | guided SR · Depth map SR (x32) | MSE (pixel^2): 1343.3 -> 26.0 | Improved |
| use pixel-to-pixel mapping instead of HR-trained MSG-Net | guided SR · Depth map SR (x16) | MSE (pixel^2): 12.4 -> 8.4 | Improved |
| use pixel-to-pixel mapping instead of MSG-Net-DS | guided SR · Depth map SR (x8) | MSE (pixel^2): 8.3 -> 5.6 | Improved |
| use pixel-to-pixel mapping instead of MSG-Net-DS | guided SR · Depth map SR (x4) | MSE (pixel^2): 1.9 -> 5.0 | Hurt |
| use pixel-to-pixel mapping instead of SD filter | guided SR · Depth map SR (x4) | PBP delta=1 (%): 4.5 -> 6.9 | Hurt |
| use pixel-to-pixel mapping instead of bicubic | guided SR · Vegetation height SR (x8) | MSE (m^2): 18.1 -> 17.6 | No clear effect |
| use pixel-to-pixel mapping instead of bicubic | guided SR · Vegetation height SR (x16) | MSE (m^2): 29.1 -> 19.7 | Improved |
| use pixel-to-pixel mapping instead of bicubic | guided SR · Vegetation height SR (x32) | MSE (m^2): 41.5 -> 21.2 | Improved |
| use pixel-to-pixel mapping instead of HR-trained MSG-Net | guided SR · Vegetation height SR (x32) | MSE (m^2): 44.3 -> 21.2 | Improved |
| use pixel-to-pixel mapping instead of HR-trained MSG-Net | guided SR · Vegetation height SR (x8) | MSE (m^2): 16.3 -> 17.6 | Hurt |
Closest papers by meaning
- Learning Graph Regularisation for Guided Super-Resolution (CVPR 2022 · similarity 0.90)
- Guided Depth Super-Resolution by Deep Anisotropic Diffusion (CVPR 2023 · similarity 0.88)
- Exploiting Raw Images for Real-Scene Super-Resolution (TPAMI 2020 · similarity 0.88)
- Auto-Encoded Supervision for Perceptual Image Super-Resolution (CVPR 2025 · similarity 0.87)
- SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-resolution (AAAI 2024 · similarity 0.86)
- Transformer-Based Selective Super-resolution for Efficient Image Refinement (AAAI 2024 · similarity 0.86)
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.
