Research map / 3D vision / Depth and stereo
Spatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising
Guanting Dong, Yueyi Zhang, Zhiwei Xiong
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 Residual Fusion Module (ablation) | SHARP-Net · TFT3D | overall MAE (cm): 1.55 -> 1.19 | Improved |
| add Depth Refinement Module (ablation) | SHARP-Net · TFT3D | overall MAE (cm): 1.62 -> 1.19 | Improved |
| add both Residual Fusion and Depth Refinement Modules (ablation) | SHARP-Net · TFT3D | overall MAE (cm): 1.69 -> 1.19 | Improved |
| add both Residual Fusion and Depth Refinement Modules (ablation) | SHARP-Net · TFT3D | overall relative error: 13.8% -> 9.7% | Improved |
| increase pyramid levels from 4 to 6 (ablation) | SHARP-Net · TFT3D | overall MAE (cm): 1.78 -> 1.19 | Improved |
| increase pyramid levels from 5 to 6 (ablation) | SHARP-Net · TFT3D | overall MAE (cm): 1.53 -> 1.19 | Improved |
| increase pyramid levels from 4 to 5 (ablation) | SHARP-Net · TFT3D | overall MAE (cm): 1.78 -> 1.53 | Improved |
| use SHARP-Net instead of ToF-KPN | SHARP-Net vs ToF-KPN · TFT3D | overall MAE (cm): 2.38 -> 1.19 | Improved |
| use SHARP-Net instead of ToF-KPN | SHARP-Net vs ToF-KPN · FLAT | overall MAE (cm): 0.79 -> 0.46 | Improved |
| use SHARP-Net instead of ToF-KPN | SHARP-Net vs ToF-KPN · True Box | overall MAE (cm): 1.82 -> 1.14 | Improved |
| use SHARP-Net instead of ToF-KPN at lower error levels | SHARP-Net vs ToF-KPN · FLAT | relative error, first three quantiles: 24.2% -> 12.1% | No clear effect |
| use SHARP-Net instead of DeepToF | SHARP-Net vs DeepToF · TFT3D | overall MAE (cm): 3.54 -> 1.19 | Improved |
Closest papers by meaning
- Depth Restoration in Under-Display Time-of-Flight Imaging (TPAMI 2022 · similarity 0.89)
- Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention (ICCV 2025 · similarity 0.89)
- Exploiting Dual-Correlation for Multi-frame Time-of-Flight Denoising (ECCV 2024 · similarity 0.88)
- Deep End-to-End Time-of-Flight Imaging (CVPR 2018 · similarity 0.88)
- SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion (CVPR 2025 · similarity 0.85)
- Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing (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.
