Research map / Optimization / Optimizers
Auto-Tuning Structured Light by Optical Stochastic Gradient Descent
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 |
|---|---|---|---|
| Optimize projection patterns and decoder together with optical SGD instead of using fixed coding patterns | LG-IDS structured-light system · LG-IDS example scene, 0-tolerance | pixels with no correspondence error: 62% -> 72% | Helped |
| Optimize projection patterns and decoder together with optical SGD instead of using fixed coding patterns | LG-IDS structured-light system · LG-IDS example scene, L1 | average correspondence error: 4.7 -> 3.7 | Helped |
| Use ZNCC5 neighborhood decoding instead of ZNCC pixel-only decoding (ablation) | LG-IDS structured-light system with auto-tuned patterns · LG-IDS example scene, 0-tolerance | pixels with no correspondence error: 32% -> 67% | Helped |
| Use ZNCC-NN5 neighborhood decoder instead of ZNCC5 (ablation) | LG-IDS structured-light system with auto-tuned patterns · LG-IDS example scene, 0-tolerance | pixels with no correspondence error: 67% -> 72% | Helped |
| Use ZNCC5 neighborhood decoding instead of ZNCC pixel-only decoding (ablation) | LG-IDS structured-light system with auto-tuned patterns · LG-IDS example scene, L1 | average correspondence error: 9.8 -> 4.2 | Helped |
| Use ZNCC-NN5 instead of ZNCC5 (ablation) | LG-IDS structured-light system with auto-tuned patterns · LG-IDS example scene, L1 | average correspondence error: 4.2 -> 3.7 | Helped |
| Use a beeswax training scene at 40cm, Hadamard multiplexing for Jacobian acquisition, and refinement with higher softmax temperature | EpiScan3D optical SGD · Beeswax scene at 80cm, 2-tolerance | pixels with correspondence error ≤2: 79% -> 87% | Helped |
| Train on a beeswax scene rather than the board (ablation) | EpiScan3D optical SGD · Beeswax scene at 80cm, 2-tolerance | pixels with correspondence error ≤2: 46% -> 75% | Helped |
Closest papers by meaning
- Optimal Structured Light à La Carte (CVPR 2018 · similarity 0.86)
- TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light (CVPR 2024 · similarity 0.86)
- Differentiable Adaptive 4D Structured Illumination for Joint Capture of Shape and Reflectance (CVPR 2026 · similarity 0.85)
- Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment (CVPR 2025 · similarity 0.83)
- MetaGS: A Meta-Learned Gaussian-Phong Model for Out-of-Distribution 3D Scene Relighting (NeurIPS 2025 · similarity 0.83)
- DiffusionLight: Light Probes for Free by Painting a Chrome Ball (CVPR 2024 · 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.