Research map / 3D vision / Depth and stereo
Depth from Coupled Optical Differentiation
Junjie Luo, Yuxuan Liu, Emma Alexander, Qi Guo
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 coupled optical derivatives only instead of the second-order spatial derivative (Focal Track) | depth from defocus · Simulation, working range | working range: 20 cm -> 80 cm | Improved |
| coupled optical differentiation vs Focal Track and DfDW on real prototype | prototype sensor · Real scenes (11 textured planes) | working range and computation: more than 2x longer working range at 6% and 1% computation | Improved |
| add confidence-threshold filtering (higher sparsity) (ablation) | coupled optical differentiation · Simulation | depth MAE: 70 mm -> 20 mm | Improved |
| use pillbox aperture transmittance instead of Gaussian, smooth-disk or multi-pillbox (ablation) | coupled optical differentiation · Simulation, aperture profiles | depth MAE | Improved |
| aggregate derivatives over a larger window (5x5 chosen at elbow) (ablation) | coupled optical differentiation · Simulation | depth MAE: 5x5 window at elbow point | Improved |
| increase confidence level on real prototype (ablation) | coupled optical differentiation · Real data | working range | Improved |
Closest papers by meaning
- Energy-Efficient Adaptive 3D Sensing (CVPR 2023 · similarity 0.87)
- Depth From Semi-Calibrated Stereo and Defocus (CVPR 2016 · similarity 0.86)
- Shape Estimation from Shading, Defocus, and Correspondence Using Light-Field Angular Coherence (TPAMI 2016 · similarity 0.86)
- Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging (CVPR 2024 · similarity 0.86)
- Focal Split: Untethered Snapshot Depth from Differential Defocus (CVPR 2025 · similarity 0.84)
- Coherence As Texture - Passive Textureless 3D Reconstruction by Self-interference (CVPR 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.
