Research map / Image generation / Super-resolution
Stereoscopic Image Super-Resolution with Stereo Consistent Feature
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 parallax-attention (+P) to baseline (ablation) | stereo SR baseline · Middlebury 4x | PSNR: 29.85 -> 29.98 | Helped |
| add parallax-attention (+P) to baseline (ablation) | stereo SR baseline · Middlebury 4x | SSIM: 0.901 -> 0.919 | Helped |
| add parallax-attention (+P) to baseline (ablation) | stereo SR baseline · Middlebury 4x | warping error: 0.000361 -> 0.000328 | Helped |
| add self-attention (+S) (ablation) | baseline+P · Middlebury 4x | PSNR: 29.98 -> 30.08 | Helped |
| add self-attention (+S) (ablation) | baseline+P · Middlebury 4x | warping error: 0.000328 -> 0.000327 | No clear effect |
| add stereo-consistency loss (+C) (ablation) | baseline+P+S · Middlebury 4x | warping error: 0.000327 -> 0.000259 | Helped |
| add stereo-consistency loss (+C) (ablation) | baseline+P+S · Middlebury 4x | PSNR: 30.08 -> 30.11 | Helped |
| SPAM with stereo-consistency loss vs PASSRnet | stereo SR · Flickr 1024 4x | PSNR / SSIM: 23.21 / 0.779 -> 23.35 / 0.787 | Helped |
| SPAM with stereo-consistency loss vs PASSRnet | stereo SR · Middlebury 4x | warping error: 0.000291 -> 0.000259 | Helped |
Closest papers by meaning
- Learning Parallax Attention for Stereo Image Super-Resolution (CVPR 2019 · similarity 0.90)
- DIFFSSR: Stereo Image Super-resolution Using Differential Transformer (NeurIPS 2025 · similarity 0.86)
- Enhancing the Spatial Resolution of Stereo Images Using a Parallax Prior (CVPR 2018 · similarity 0.85)
- Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues (CVPR 2025 · similarity 0.83)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.83)
- Differentiable Display Photometric Stereo (CVPR 2024 · similarity 0.82)
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.