Research map / 3D vision / Depth and stereo
Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation
Fengchen He, Dayang Zhao, Hao Xu, Tingwei Quan, Shaoqun Zeng
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 |
|---|---|---|---|
| simulate DP PSFs with ray tracing instead of CoC | DP PSF simulation · Real vs simulated F/1.8 DP PSFs | NCC: 0.672 -> 0.915 | Improved |
| simulate DP PSFs with ray tracing instead of CoC | DP PSF simulation · Real vs simulated F/1.8 DP PSFs | NSD: 0.448 -> 0.133 | Improved |
| train DfDP on Sdirt images instead of CoC images | DfDP · DP119 Planar | MAE: 0.2085 -> 0.0845 | Improved |
| train DfDP on Sdirt images instead of CoC images | DfDP · DP119 Box | Acc-1: 0.4412 -> 0.9474 | Improved |
| train DfDP on Sdirt images instead of CoC images | DfDP · DP119 Casual | Acc-1: 0.3318 -> 0.8236 | Improved |
| train DfDP on Sdirt images instead of CoC images | DfDP · DP119 Casual | Sq.r.: 0.6821 -> 0.7241 | Mixed |
| train DfDP on Sdirt images instead of Modeling images | DfDP · DP119 Casual | MAE: 0.7934 -> 0.2702 | Improved |
| predict DP PSFs with MLP network instead of ray tracing | DP PSF prediction · DP PSF prediction time | time (s): 801.544 -> 0.395 | Improved |
| use our MLP PSF network instead of Yang et al. | DP PSF prediction · DP PSF prediction (F/4, 50 depths and positions) | L1 error: 1.487e-4 -> 6.887e-5 | Improved |
| use our MLP PSF network instead of Tseng et al. | DP PSF prediction · DP PSF prediction (F/4, 50 depths and positions) | prediction time (s): 43.96 -> 0.395 | Improved |
Closest papers by meaning
- All-directional Disparity Estimation for Real-world QPD Images (CVPR 2025 · similarity 0.84)
- Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging (CVPR 2024 · similarity 0.83)
- DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation (AAAI 2024 · similarity 0.83)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.83)
- Dual Exposure Stereo for Extended Dynamic Range 3D Imaging (CVPR 2025 · similarity 0.83)
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · 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.
