# iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imaging

arXiv: https://arxiv.org/abs/2103.07087 · HTML: https://mlsanity.com/paper/2103.07087/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 66 references that are in the map.
- First posted on arXiv 12 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [Asynchronous Single-Photon 3D Imaging](https://mlsanity.com/paper/1908.06372/) (2019)
- [Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset](https://mlsanity.com/paper/1807.10376/) (2018)
- [Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module](https://mlsanity.com/paper/1909.07623/) (2019)
- [DeepToF: Off-the-Shelf Real-Time Correction of Multipath Interference in Time-of-Flight Imaging](https://mlsanity.com/paper/1805.09305/) (2018)
- [Recent Advances in Transient Imaging: A Computer Graphics and Vision Perspective](https://mlsanity.com/paper/1611.00939/) (2016)
- [Learning to Remove Multipath Distortions in Time-of-Flight Range Images for a Robotic Arm Setup](https://mlsanity.com/paper/1601.01750/) (2016)
- [SRA: Fast Removal of General Multipath for ToF Sensors](https://mlsanity.com/paper/1403.5919/) (2014)
- [Bayesian Time-of-Flight for Realtime Shape, Illumination and Albedo](https://mlsanity.com/paper/1507.06173/) (2015)
- [Very Power Efficient Neural Time-of-Flight](https://mlsanity.com/paper/1812.08125/) (2018)
- [Long-range depth imaging using a single-photon detector array and non-local data fusion](https://mlsanity.com/paper/1812.04943/) (2018)

## Built on by (most cited first, 11 of 11)

- [Consistent Direct Time-of-Flight Video Depth Super-Resolution](https://mlsanity.com/paper/2211.08658/) (2022)
- [RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methods](https://mlsanity.com/paper/2405.10357/) (2024)
- [RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising](https://mlsanity.com/paper/2111.15513/) (2021)
- [Count-Free Single-Photon 3D Imaging with Race Logic](https://mlsanity.com/paper/2307.04924/) (2023)
- [Single-Photon 3D Imaging with Equi-Depth Photon Histograms](https://mlsanity.com/paper/2408.16150/) (2024)
- [Lightweight Deep Learning Architecture for MPI Correction and Transient Reconstruction](https://mlsanity.com/paper/2111.14396/) (2021)
- [Weakly-Supervised Optical Flow Estimation for Time-of-Flight](https://mlsanity.com/paper/2210.05298/) (2022)
- [Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention](https://mlsanity.com/paper/2506.23542/) (2025)
- [Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light](https://mlsanity.com/paper/2512.06080/) (2025)
- [High-Flux Count-Free Single-Photon 3D Cameras](https://mlsanity.com/paper/2608.18306/) (2026)
- [Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restoration](https://mlsanity.com/paper/2609.05507/) (2026)

## Abstract (arXiv)

Indirect Time-of-Flight (iToF) cameras are a promising depth sensing technology. However, they are prone to errors caused by multi-path interference (MPI) and low signal-to-noise ratio (SNR). Traditional methods, after denoising, mitigate MPI by estimating a transient image that encodes depths. Recently, data-driven methods that jointly denoise and mitigate MPI have become state-of-the-art without using the intermediate transient representation. In this paper, we propose to revisit the transient representation. Using data-driven priors, we interpolate/extrapolate iToF frequencies and use them to estimate the transient image. Given direct ToF (dToF) sensors capture transient images, we name our method iToF2dToF. The transient representation is flexible. It can be integrated with different rule-based depth sensing algorithms that are robust to low SNR and can deal with ambiguous scenarios that arise in practice (e.g., specular MPI, optical cross-talk). We demonstrate the benefits of iToF2dToF over previous methods in real depth sensing scenarios.