mlsanityData to 14 Oct 2026

RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising

arXiv 2111.15513 ↗First posted 30 Nov 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI). While recent research showed that 2D neural networks are able to outperform previous traditional State-of-the-Art (SOTA) methods on denoising ToF-Data, little research on learning-based approaches has been done to make direct use of the 3D information present in depth images. In this paper, we propose an iterative denoising approach operating in 3D space, that is designed to learn on 2.5D data by enabling 3D point convolutions to correct the points' positions along the view direction. As labeled real world data is scarce for this task, we further train our network with a self-training approach on unlabeled real world data to account for real world statistics. We demonstrate that our method is able to outperform SOTA methods on several datasets, including two real world datasets and a new large-scale synthetic data set introduced in this paper.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 24 of its 44 references that are in the map. First posted on arXiv 30 Nov 2021.

Builds on

24 of 44 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  5. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  6. 2019Confidence Regularized Self-Trainingcited by 419
  7. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 183
  8. 2020Understanding Self-Training for Gradual Domain Adaptationcited by 149
  9. 2021Cycle Self-Training for Domain Adaptationcited by 120
  10. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  11. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  12. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
12 more
  1. 2020SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptationcited by 78
  2. 2018Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Cloudscited by 62
  3. 2019Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaningcited by 58
  4. 2020In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustnesscited by 50
  5. 2018Tackling 3D ToF Artifacts Through Learning and the FLAT Datasetcited by 21
  6. 2019Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Modulecited by 14
  7. 2018DeepToF: Off-the-Shelf Real-Time Correction of Multipath Interference in Time-of-Flight Imagingcited by 13
  8. 2016Learning to Remove Multipath Distortions in Time-of-Flight Range Images for a Robotic Arm Setupcited by 11
  9. 2021iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imagingcited by 11
  10. 2014SRA: Fast Removal of General Multipath for ToF Sensorscited by 10
  11. 2018Very Power Efficient Neural Time-of-Flightcited by 8
  12. 2018Depth Reconstruction of Translucent Objects from a Single Time-of-Flight Camera using Deep Residual Networkscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 2; 2026: 1.

5 papers.

  1. 2023Self-Annotated 3D Geometric Learning for Smeared Points Removalcited by 3
  2. 2022Weakly-Supervised Optical Flow Estimation for Time-of-Flightcited by 1
  3. 2025Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attentioncited by 1
  4. 2025Towards Robust Time-of-Flight Depth Denoising with Confidence-Aware Diffusion Modelcited by 0
  5. 2026Reliable iToF Depth Sensing via Sensor-Intrinsic Uncertainty Modeling and State-Space Restorationcited by 0