Research map / Video / Video segmentation and tracking
Dynamic Time-Of-Flight
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 |
|---|---|---|---|
| integrate two frames instead of using one frame with the SP model | TOF depth inference · 2F-TP in-model validation | absolute error 50% quantile (cm): 9.20 -> 7.78 | Helped |
| integrate two frames instead of using one frame with the TP model | TOF depth inference · 2F-TP in-model validation | absolute error 75% quantile (cm): 21.70 -> 14.48 | Helped |
| use a two-path observation model instead of a single-path model | TOF depth inference · 2F-TP in-model validation | absolute error 75% quantile (cm): 16.82 -> 14.48 | Helped |
| use complementary measurement patterns across frames instead of repeating one pattern (ablation) | 2F-SP and 2F-TP · dynamic measurement design validation | absolute depth error | Helped |
| add a mixture fallback to the independent prior rather than use only the temporal motion model (ablation) | 2F-SP and 2F-TP · rendering simulations with motion | absolute depth error | Helped |
| use spatial guided filtering on the depth output (ablation) | TOF depth estimates · five simulated scenes | absolute depth error | Helped |
| apply temporal filtering to depth outputs instead of integrating raw IR observations (ablation) | spatio-temporal depth baseline · five simulated scenes | absolute depth error | No clear effect |
| use the robust mixture dynamics instead of the non-robust motion model with ω = 0 (ablation) | 2F-SP and 2F-TP · large-motion rendering simulations | absolute depth error | Helped |
Closest papers by meaning
- Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing (NeurIPS 2025 · similarity 0.88)
- Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction (CVPR 2024 · similarity 0.86)
- SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion (CVPR 2025 · similarity 0.83)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.83)
- Seurat: From Moving Points to Depth (CVPR 2025 · similarity 0.83)
- Video Depth Anything: Consistent Depth Estimation for Super-Long Videos (CVPR 2025 · 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.