Research map / 3D vision / Depth and stereo
Depth From Semi-Calibrated Stereo and Defocus
Ting-Chun Wang, Manohar Srikanth, Ravi Ramamoorthi
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 semi-calibrated three-camera rectification instead of Fusiello et al. rectification | Main/side image rectification · Rectification image 1 | average Sampson error: 1.3795 -> 0.7433 | Improved |
| Use semi-calibrated three-camera rectification instead of Fusiello et al. rectification | Main/side image rectification · Rectification image 4 | average Sampson error: 0.9839 -> 0.8865 | Improved |
| Combine stereo with defocus refinement (ablation) | Depth estimation system · Indoor scenes | depth RMSE: 0.0568 -> 0.0558 | Improved |
| Use defocus cues only instead of combining them with stereo (ablation) | Depth estimation system · Indoor scenes | depth RMSE: 0.0651 -> 0.0558 | Hurt |
| Combine stereo and defocus cues rather than relying on depth upsampling | Depth estimation system · Indoor scenes | depth RMSE: 0.0605 -> 0.0558 | Improved |
| Combine stereo and defocus cues rather than using Lytro Illum depth | Depth estimation system · Indoor scenes | depth RMSE: 0.0655 -> 0.0558 | Improved |
Closest papers by meaning
- Finite Aperture Stereo (IJCV 2022 · similarity 0.87)
- Depth from Coupled Optical Differentiation (IJCV 2025 · similarity 0.86)
- Depth From Defocus in the Wild (CVPR 2017 · similarity 0.86)
- Focal Split: Untethered Snapshot Depth from Differential Defocus (CVPR 2025 · similarity 0.83)
- All-directional Disparity Estimation for Real-world QPD Images (CVPR 2025 · similarity 0.83)
- Learned Binocular-Encoding Optics for RGBD Imaging Using Joint Stereo and Focus Cues (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.
