Research map / Image generation / Super-resolution
Cross-MPI: Cross-Scale Stereo for Image Super-Resolution Using Multiplane Images
Yuemei Zhou, Gaochang Wu, Ying Fu, Kun Li, Yebin Liu
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 Cross-MPI instead of CrossNet-8× | 8× RefSR on RealEstate10K, frame diff. = 9 · RealEstate10K, frame diff. = 9 | PSNR: 32.914 -> 32.878 | No clear effect |
| use Cross-MPI instead of TTSR-8× | 8× RefSR on RealEstate10K, frame diff. = 9 · RealEstate10K, frame diff. = 9 | SSIM: 0.923 -> 0.937 | Improved |
| use Cross-MPI instead of TTSR-8× | 8× RefSR on RealEstate10K, frame diffs. 11–23 · RealEstate10K | PSNR: 31.002 -> 31.736; 30.383 -> 30.993; 29.843 -> 30.360; 29.405 -> 29.852 | Improved |
| use Cross-MPI instead of TTSR-8× | 8× RefSR on RealEstate10K, frame diffs. 11–23 · RealEstate10K | SSIM: 0.908 -> 0.921; 0.896 -> 0.909; 0.884 -> 0.896; 0.874 -> 0.885 | Mixed |
| use Cross-MPI instead of CrossNet-8× | 8× RefSR on optical zoom-in data · Optical zoom-in dataset | PSNR: 27.830 -> 29.209 | Improved |
| use Cross-MPI instead of CrossNet-8× | 8× RefSR on optical zoom-in data · Optical zoom-in dataset | SSIM: 0.798 -> 0.841 | Improved |
| add plane-aware attention rather than concatenation + convolution (ablation) | Cross-MPI · Cross-MPI ablation test, frame diffs. 3–10 | PSNR: 33.015 -> 33.100 | Improved |
| add plane-aware attention rather than concatenation + convolution (ablation) | Cross-MPI · Cross-MPI ablation test, frame diffs. 3–10 | SSIM: 0.93266 -> 0.93275 | Improved |
| add external guidance to multiscale guided upsampling (ablation) | Cross-MPI · Cross-MPI ablation test, frame diffs. 3–10 | PSNR: 32.981 -> 33.100 | Improved |
| add external guidance to multiscale guided upsampling (ablation) | Cross-MPI · Cross-MPI ablation test, frame diffs. 3–10 | SSIM: 0.93269 -> 0.93275 | Improved |
| add internal supervision loss (ablation) | Cross-MPI · Cross-MPI ablation test, frame diffs. 3–10 | PSNR: 32.982 -> 33.100 | Improved |
| add internal supervision loss (ablation) | Cross-MPI · Cross-MPI ablation test, frame diffs. 3–10 | SSIM: 0.93045 -> 0.93275 | Improved |
Closest papers by meaning
- CrossNet++: Cross-Scale Large-Parallax Warping for Reference-Based Super-Resolution (TPAMI 2020 · similarity 0.87)
- Dual-Camera Super-Resolution With Aligned Attention Modules (ICCV 2021 · similarity 0.86)
- Learning Parallax Attention for Stereo Image Super-Resolution (CVPR 2019 · similarity 0.86)
- CrossNet: An End-to-end Reference-based Super Resolution Network using Cross-scale Warping (ECCV 2018 · similarity 0.86)
- EC-MVSNet: Enhanced Cascaded Multi-View Stereo with Cross-Scale Relevance Integration (AAAI 2026 · similarity 0.85)
- Multi-view Reconstruction via SfM-guided Monocular Depth Estimation (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.
