Research map / 3D vision / Depth and stereo
Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset
Qi Guo, Iuri Frosio, Orazio Gallo, Todd Zickler, Jan Kautz
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 the motion module (MOM) to the LF2 pipeline (ablation) | LF2 on Kinect 2 · FLAT test set (MPI, shot noise, random motion) | density (percentage of reconstructed pixels): 93.56% to 95.50% | Improved |
| add the multi-reflection module (MRM) after MOM (ablation) | MOM · FLAT test set (MPI, shot noise, random motion) | density and MPI bias | Improved |
| replace the raw-domain network with one that outputs depth directly (ablation) | MOM-MRM · FLAT | depth reconstruction error | Hurt |
| fine tune with physically accurate second motion approximation instead of the first (ablation) | MOM-MRM · FLAT | depth error | No clear effect |
Closest papers by meaning
- Deep End-to-End Time-of-Flight Imaging (CVPR 2018 · similarity 0.89)
- Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging (CVPR 2021 · similarity 0.88)
- RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising (CVPR 2022 · similarity 0.88)
- Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors (CVPR 2026 · similarity 0.87)
- Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing (NeurIPS 2025 · similarity 0.85)
- Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction (CVPR 2024 · similarity 0.85)
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.
