Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration

Abstract

Indirect time-of-flight (iToF) cameras provide compact and cost-effective dense depth measurements, but their ranging accuracy is often degraded by sensor-intrinsic uncertainty under practical imaging conditions. Spatially uniform or range-only Gaussian perturbations cannot accurately reproduce the range-dependent and signal-dependent noise characteristics of real iToF measurements, leading to a synthetic-to-real gap for learning-based restoration. To address this problem, we propose a joint depth-uncertainty modeling and restoration framework for reliable iToF sensing. A sensor-intrinsic depth-uncertainty model is first developed from calibrated tap responses, returned-signal levels, and sensor noise statistics through a depth-oriented weighted least-squares formulation. The resulting pixel-wise uncertainty is used for heteroscedastic depth synthesis and uncertainty-aware restoration supervision. Based on this heteroscedastic data synthesis, we further develop a U-shaped restoration network with Depth Visual State Space (DVSS) blocks, which combine long-range state-space modeling with convolutional spatial-channel refinement for structure-preserving depth recovery. Experiments on synthetic data and measurements captured by an in-house iToF prototype validate the proposed uncertainty model under varying range and returned-signal conditions. Controlled comparisons with fixed and range-aware Gaussian noise, together with evaluations on U-Net, Restormer, and DVSS, further demonstrate that the proposed synthesis consistently benefits different restoration backbones. The complete framework achieves 40.85~dB PSNR and 2.54 mm MAE on the synthetic test set, and 35.42 dB PSNR and 4.87 mm MAE on real iToF measurements.

Reliable Uncertainty Estimation for Machine-Learned Multigroup Cross Sections Without Retraining
Joshua Nichols, Andrew Osborne, Valerio Mascolino
arXiv6 Oct 2026PreprintCC BY 4.0Full textComputational physicsarXiv
Acquisition-inspired motion artifact modeling and degradation-consistent diffusion restoration in photoacoustic microscopy
Heqing Wang, Shuyan Zhang, Jingtan Li +3
Photoacoustics29 Oct 2026Peer-reviewedCC BYFull textOptics & photonicsDOAJ
A model of grain growth in UN integrating molecular dynamics, phase-field modeling, and uncertainty quantification
Mohamed AbdulHameed, Fadel M. Nasr, Wen Jiang +2
arXiv10 Sep 2026PreprintCC BY 4.0Full textCondensed matterarXiv
Interval and fuzzy physics-augmented neural networks (iPANN and fPANN) for uncertainty quantification and propagation in constitutive modeling
Somesh Pratap Singh, Govinda Anantha Padmanabha, Jingye Tan +4
arXiv26 Sep 2026PreprintarXiv licenceFull textComputational physicsarXiv
Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing
Ling-Wei Kong, Ying-Cheng Lai
arXiv1 Sep 2026PreprintarXiv licenceFull textStatistical & nonlinear physicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{du2026reliable,
  title = {{Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration}},
  author = {Yansong Du and Yutong Deng and Yuting Zhou and Zhancong Xu and Yingjia Lu and Mengdi Wang and Feiyu Jiao and Bangyao Wang and Zhaoxiang Jiang and Xun Guan},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.05507},
  eprint = {2609.05507},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.05507},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration
AU  - Yansong Du
AU  - Yutong Deng
AU  - Yuting Zhou
AU  - Zhancong Xu
AU  - Yingjia Lu
AU  - Mengdi Wang
AU  - Feiyu Jiao
AU  - Bangyao Wang
AU  - Zhaoxiang Jiang
AU  - Xun Guan
PY  - 2026
DA  - 2026/09/01
PB  - arXiv
DO  - 10.48550/arxiv.2609.05507
UR  - https://arxiv.org/abs/2609.05507
AB  - Indirect time-of-flight (iToF) cameras provide compact and cost-effective dense depth measurements, but their ranging accuracy is often degraded by sensor-intrinsic uncertainty under practical imaging conditions. Spatially uniform or range-only Gaussian perturbations cannot accurately reproduce the range-dependent and signal-dependent noise characteristics of real iToF measurements, leading to a synthetic-to-real gap for learning-based restoration. To address this problem, we propose a joint depth-uncertainty modeling and restoration framework for reliable iToF sensing. A sensor-intrinsic depth-uncertainty model is first developed from calibrated tap responses, returned-signal levels, and sensor noise statistics through a depth-oriented weighted least-squares formulation. The resulting pixel-wise uncertainty is used for heteroscedastic depth synthesis and uncertainty-aware restoration supervision. Based on this heteroscedastic data synthesis, we further develop a U-shaped restoration network with Depth Visual State Space (DVSS) blocks, which combine long-range state-space modeling with convolutional spatial-channel refinement for structure-preserving depth recovery. Experiments on synthetic data and measurements captured by an in-house iToF prototype validate the proposed uncertainty model under varying range and returned-signal conditions. Controlled comparisons with fixed and range-aware Gaussian noise, together with evaluations on U-Net, Restormer, and DVSS, further demonstrate that the proposed synthesis consistently benefits different restoration backbones. The complete framework achieves 40.85~dB PSNR and 2.54 mm MAE on the synthetic test set, and 35.42 dB PSNR and 4.87 mm MAE on real iToF measurements.
ER  -

Abstract

Related

Cite