Research map / 3D vision / Depth and stereo
A Practical Stereo Depth System for Smart Glasses
Read the paperCheck 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 |
|---|---|---|---|
| Train Argos on the rendered internal stereo dataset instead of Sceneflow | Argos · Middlebury 2014 training set | AbsRel: 0.107 -> 0.075 | Helped |
| Use stereo Argos depth instead of monocular Tiefenrausch depth | Rendered novel-view videos · Smart-glasses scenes | Survey score: 2.96 -> 3.44 | Helped |
| Add relative scale Δf estimation to relative-rotation rectification (ablation) | Online rectification · 185 challenging test image pairs | Success rate: 142/185= 77% -> 157/185= 85% | Helped |
| Add relative scale Δf estimation to relative-rotation rectification (ablation) | Online rectification · 185 challenging test image pairs | Median inlier rate: 80% -> 85% | Helped |
| Add relative scale Δf estimation to relative-rotation rectification (ablation) | Online rectification · 185 challenging test image pairs | Error Δf: 0.083% -> 0.024% | Helped |
| Use Argos stereo depth rather than Tiefenrausch monocular depth | Middlebury 2014 training set · Middlebury 2014 training set | AbsRel: 0.253 -> 0.075 | Helped |
| Use 8-bit quantization-aware training rather than post-training quantization | Argos · Stereo depth estimation | Accuracy | Helped |
Closest papers by meaning
- Energy-Efficient Adaptive 3D Sensing (CVPR 2023 · similarity 0.87)
- A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos (CVPR 2017 · similarity 0.87)
- Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses (CVPR 2025 · similarity 0.86)
- Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail (CVPR 2025 · similarity 0.85)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.84)
- PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching (NeurIPS 2025 · 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.