Research map / Image generation / Image restoration
Disparity-Aware Domain Adaptation in Stereo Image Restoration
Check 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 |
|---|---|---|---|
| Use stereo-aware DASSR instead of the strongest listed baseline | Stereo image SR · SceneFlow ×4 | PSNR: 31.59 -> 33.35 | Helped |
| Add cross-view disparity-guided restoration | Stereo image SR · KITTI 2012 ×4 | PSNR: 27.60 -> 26.96 | Hurt |
| Add binocular reference information to monocular restoration (ablation) | StereoIRN · Middlebury ×4 SR | PSNR: 28.987 -> 29.423 | Helped |
| Add feature transmission between NETM and NETB (ablation) | StereoIRN · Middlebury ×4 SR | PSNR: 29.423 -> 29.722 | Helped |
| Add disparity flow network instead of using PWCNet (ablation) | StereoIRN · Middlebury ×4 SR | PSNR: 29.625 -> 29.831 | Helped |
| Use FMDB instead of concatenation, 3D convolution, or parallel paths (ablation) | StereoIRN binocular network · Middlebury ×4 SR | PSNR: 29.16 -> 29.83; 27.79 -> 29.83; 29.60 -> 29.83 | Helped |
| Add disparity content loss (ablation) | StereoIRN · SceneFlow A-000 ×4 SR | EPE: 2.4982 -> 2.3665 | Helped |
| Add disparity perceptual loss (ablation) | StereoIRN · SceneFlow A-000 ×4 SR | EPE: 2.4982 -> 2.2996 | Helped |
| Optimize with disparity content or perceptual loss rather than MSE alone (ablation) | StereoIRN · SceneFlow A-000 ×4 SR | PSNR: 33.223 -> 32.757; 33.223 -> 32.673 | Hurt |
Closest papers by meaning
- DispViT: Direct Stereo Disparity Regression with a Single-Stream Vision Transformer (ICLR 2026 · similarity 0.87)
- Revisiting Domain Generalized Stereo Matching Networks From a Feature Consistency Perspective (CVPR 2022 · similarity 0.86)
- StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching (CVPR 2020 · similarity 0.86)
- DEFOM-Stereo: Depth Foundation Model Based Stereo Matching (CVPR 2025 · similarity 0.85)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.85)
- Modeling Stereo-Confidence out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep (AAAI 2024 · similarity 0.84)
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.