Research map / 3D vision / Depth and stereo
Recovering Transparent Shape From Time-Of-Flight Distortion
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 |
|---|---|---|---|
| Use normal consistency to estimate the front surface depth | Baseline method · Simulation, 48 transparent shapes | average reconstruction error: 0.45 % | Helped |
| Add denoising of ToF measurements before optimization (ablation) | Transparent shape reconstruction · Simulated ToF measurements with varying noise | reconstruction error | Helped |
| Use alternating optimization of shape and ToF measurement denoising (ablation) | Transparent shape reconstruction · Simulated ToF measurements with varying noise | reconstruction error | Helped |
| Combine alternating optimization with denoising (ablation) | Transparent shape reconstruction · Simulated ToF measurements with varying noise | reconstruction error | Helped |
| Add a retroreflective sheet behind the object (ablation) | Transparent shape reconstruction · Right angle prism | mean reconstruction error: 0.745 mm -> 0.448 mm | Helped |
| Add a retroreflective sheet behind the object (ablation) | Transparent shape reconstruction · Right angle prism | standard deviation of reconstruction error: 1.115 mm -> 0.828 mm | Helped |
| Initialize front depth within the reported successful interval (ablation) | Baseline method · Simulation, object spanning 200 mm to 250 mm | reconstruction error: less than 1% | Helped |
Closest papers by meaning
- 3D Reconstruction of Transparent Objects With Position-Normal Consistency (CVPR 2016 · similarity 0.88)
- Trapping Light for Time of Flight (CVPR 2018 · similarity 0.87)
- Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes (CVPR 2020 · similarity 0.87)
- Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction (CVPR 2024 · similarity 0.84)
- Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing (NeurIPS 2025 · similarity 0.83)
- Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (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.