Research map / 3D vision / Depth and stereo
Deep End-to-End Time-of-Flight Imaging
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 |
|---|---|---|---|
| Replace the sequential depth pipeline with end-to-end prediction from raw dual-frequency correlations | ToF depth reconstruction · Synthetic test set, overall | MAE (m): 0.064 -> 0.029 | Helped |
| Add skip connections (ablation) | TOFNET · Synthetic test set, overall | MAE (m): 0.031 -> 0.030 | Helped |
| Add skip connections (ablation) | TOFNET · Synthetic test set, overall | SSIM: 0.9613 -> 0.9565 | Hurt |
| Add edge-aware smoothness loss (ablation) | TOFNET with skip connections · Synthetic test set, overall | SSIM: 0.9565 -> 0.9625 | Helped |
| Add edge-aware smoothness loss (ablation) | TOFNET with skip connections · Synthetic test set, overall | MAE (m): 0.030 -> 0.030 | No clear effect |
| Add adversarial loss (ablation) | TOFNET with skip connections · Synthetic test set, overall | MAE (m): 0.030 -> 0.028 | Helped |
| Add adversarial loss (ablation) | TOFNET with skip connections · Synthetic test set, overall | SSIM: 0.9565 -> 0.9593 | Helped |
| Combine skip connections, smoothness loss, and adversarial loss (ablation) | TOFNET · Synthetic test set, overall | SSIM: 0.9593 -> 0.9631 | Helped |
| Combine skip connections, smoothness loss, and adversarial loss (ablation) | TOFNET · Synthetic test set, overall | MAE (m): 0.028 -> 0.029 | Hurt |
| Use phase maps instead of raw correlations (ablation) | TOFNET · Synthetic test set, overall | MAE (m): 0.029 -> 0.055 | Hurt |
| Use phase-unwrapped depth instead of raw correlations (ablation) | TOFNET · Synthetic test set, overall | MAE (m): 0.029 -> 0.064 | Hurt |
Closest papers by meaning
- Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging (CVPR 2021 · similarity 0.89)
- Dynamic Time-Of-Flight (CVPR 2017 · similarity 0.89)
- Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing (NeurIPS 2025 · similarity 0.89)
- Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction (CVPR 2024 · similarity 0.84)
- SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion (CVPR 2025 · similarity 0.83)
- iToF-flow-based High Frame Rate Depth Imaging (CVPR 2024 · similarity 0.82)
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.