Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo
Amit Adam, Christoph Dann, Omer Yair, Shai Mazor, Sebastian Nowozin
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 |
|---|---|---|---|
| replace single-path model with two-path model (multipath) | Bayesian ToF depth inference · Simulated Sitting Room | median absolute depth error (cm): 12.50 -> 6.27 | Improved |
| replace single-path model with two-path model (multipath) | Bayesian ToF depth inference · Simulated Breakfast Room | median absolute depth error (cm): 5.69 -> 3.40 | Improved |
| replace single-path model with two-path model (multipath) | Bayesian ToF depth inference · Simulated Kitchen Nr 2 | median absolute depth error (cm): 10.29 -> 6.04 | Improved |
| replace single-path model with two-path model (multipath) | Bayesian ToF depth inference · Simulated Country Kitchen | median absolute depth error (cm): 9.63 -> 5.87 | Improved |
| replace single-path model with two-path model (multipath) | Bayesian ToF depth inference · Simulated Wooden Staircase | median absolute depth error (cm): 8.59 -> 4.85 | Improved |
| increase regression tree depth to 16 levels (ablation) | regression-tree approximation of full inference · simulated test set | error vs full inference: at 16 levels they essentially match | Improved |
| use multipath-resistant exposure profile design (beta=0.5 instead of beta=1) | exposure profile design · multipath test scene | depth bias: significant reduction in bias | Improved |
| use two-path model instead of single-path | Bayesian ToF · five simulated scenes | absolute error quantiles: typically by 40 percent | Improved |
| use two-path model instead of single-path | Bayesian ToF · five simulated scenes | inferred sigma (uncertainty): increased model sigma | Hurt |
Closest papers by meaning
- 3D Scene Inference from Transient Histograms (ECCV 2022 · similarity 0.87)
- Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields (CVPR 2025 · similarity 0.86)
- Dynamic Time-Of-Flight (CVPR 2017 · similarity 0.86)
- Snapshot Lidar: Fourier Embedding of Amplitude and Phase for Single-Image Depth Reconstruction (CVPR 2024 · similarity 0.85)
- Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing (NeurIPS 2025 · similarity 0.85)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · 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.
