Research map / 3D vision / 3D generation
Neural Inverse Rendering for High-Accuracy 3D Measurement of Moving Objects with Fewer Phase-Shifting Patterns
Yuki Urakawa, Yoshihiro Watanabe
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 |
|---|---|---|---|
| add displacement field (ablation) | PS3 two-camera · speed 2 mm/frame | MAE (mm): 0.4974 -> 0.2322 | Improved |
| add displacement field (ablation) | ALC3 two-camera · speed 2 mm/frame | MAE (mm): 0.8883 -> 0.4257 | Improved |
| add displacement field (ablation) | PS3 two-camera · speed 8 mm/frame | MAE (mm): 1.8751 -> 0.6628 | Improved |
| add second camera to single-camera ALC3 with displacement field (ablation) | ALC3 w/ DF · speed 2 mm/frame | MAE (mm): 0.6854 -> 0.4257 | Improved |
| add third camera | PS3 w/ DF · speed 4 mm/frame | MAE (mm): 0.3113 -> 0.2451 | Improved |
| add third camera | PS3 w/ DF · speed 0-2 mm/frame | MAE (mm): 0.2322 -> 0.2345 | No clear effect |
| add camera-to-camera loss (ablation) | Full method · loss ablation | MAE (mm): 8.3096 -> 0.2322 | Improved |
| add projector-to-camera loss (ablation) | Full method · loss ablation | MAE (mm): 0.3260 -> 0.2322 | Improved |
| increase patterns from 3 to 8 | Ours · Table 1 | MAE (mm): 0.2322 -> 0.3283 | Hurt |
| increase patterns from 1 to 3 | Ours · Table 1 | MAE (mm): 2.1912 -> 0.2322 | Improved |
| increase pattern frequency from 1 to 32 | Ours · Table 2 | MAE (mm): 1.1283 -> 0.2322 | Improved |
| increase pattern frequency from 32 to 64 | Ours · Table 2 | MAE (mm): 0.2322 -> 1.2778 | Hurt |
Closest papers by meaning
- Neural Inverse Rendering from Propagating Light (CVPR 2025 · similarity 0.87)
- ProbeSDF: Light Field Probes For Neural Surface Reconstruction (CVPR 2025 · similarity 0.85)
- TurboSL: Dense Accurate and Fast 3D by Neural Inverse Structured Light (CVPR 2024 · similarity 0.85)
- Real-time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured Illumination (CVPR 2024 · similarity 0.85)
- NeISF: Neural Incident Stokes Field for Geometry and Material Estimation (CVPR 2024 · similarity 0.85)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (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.
