Research map / 3D vision / Depth and stereo
FreeCam3D: Snapshot Structured Light 3D with Freely-Moving Cameras
Yicheng Wu, Vivek Boominathan, Xuan Zhao, Jacob T. Robinson, Hiroshi Kawasaki, Aswin Sankaranarayanan, Ashok Veeraraghavan
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 |
|---|---|---|---|
| replace uniform grid pattern with Kronecker-multiplexed pattern (ablation) | FreeCam3D · Simulation test, Table 1 | Lx (mm): 52.1 -> 8.3 | Improved |
| replace Kinect pattern with Kronecker-multiplexed pattern (ablation) | FreeCam3D · Simulation test, Table 1 | Lx (mm): 15.8 -> 8.3 | Improved |
| replace M-array pattern with Kronecker-multiplexed pattern (ablation) | FreeCam3D · Simulation test, Table 1 | Lz (mm): 15.5 -> 6.1 | Improved |
| replace grid pattern with Kronecker-multiplexed pattern (ablation) | FreeCam3D · Simulation test, Table 1 | Lz (mm): 8.7 -> 6.1 | Improved |
| add optimized phase mask in the projector (ablation) | FreeCam3D · Simulation test, Table 1 | Lz (mm): 90.3 -> 6.1 | Improved |
| add optimized phase mask in the projector (ablation) | FreeCam3D · Simulation test, Table 1 | Lx (mm): 8.8 -> 8.3 | Improved |
| use FreeCam3D instead of Kinect + UNet under camera misalignment | structured light depth · Camera misalignment (12 cm baseline) | Lz_c (mm): 15.7 -> 7.8 | Improved |
| use FreeCam3D instead of Kinect + DispNet under camera misalignment | structured light depth · Camera misalignment (12 cm baseline) | Lz_c (mm): 14.8 -> 7.8 | Improved |
| use FreeCam3D instead of Kinect + UNet with calibrated fixed camera | structured light depth · Fixed camera (10 cm baseline), calibrated | Lz_c (mm): 7.8 -> 7.6 | No clear effect |
| misalign camera for Kinect + UNet baseline (ablation) | Kinect + UNet · Fixed camera vs misalignment | Lz_c (mm): 7.8 -> 15.7 | Hurt |
| misalign camera for FreeCam3D (ablation) | FreeCam3D · Fixed vs misaligned camera | Lz_c (mm): 7.6 -> 7.8 | No clear effect |
Closest papers by meaning
- HyperDepth: Learning Depth From Structured Light Without Matching (CVPR 2016 · similarity 0.87)
- NeLU3D: Neural Inverse Structured Light without Modeling the Projector (ECCV 2026 · similarity 0.87)
- Optimal Structured Light à La Carte (CVPR 2018 · similarity 0.87)
- TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light (CVPR 2024 · similarity 0.86)
- Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination (CVPR 2024 · similarity 0.85)
- World Tracing: Pixel-Aligned Geometry Beyond the Visible (NeurIPS 2026 · 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.
