mlsanityData to 14 Oct 2026

Unsupervised confidence for LiDAR depth maps and applications

arXiv 2210.03118 ↗First posted 6 Oct 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Depth perception is pivotal in many fields, such as robotics and autonomous driving, to name a few. Consequently, depth sensors such as LiDARs rapidly spread in many applications. The 3D point clouds generated by these sensors must often be coupled with an RGB camera to understand the framed scene semantically. Usually, the former is projected over the camera image plane, leading to a sparse depth map. Unfortunately, this process, coupled with the intrinsic issues affecting all the depth sensors, yields noise and gross outliers in the final output. Purposely, in this paper, we propose an effective unsupervised framework aimed at explicitly addressing this issue by learning to estimate the confidence of the LiDAR sparse depth map and thus allowing for filtering out the outliers. Experimental results on the KITTI dataset highlight that our framework excels for this purpose. Moreover, we demonstrate how this achievement can improve a wide range of tasks.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 6 Oct 2022.

Builds on

34 of 54 references.

References · 34

  1. 2017Mask R-CNNcited by 7,277
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  3. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  4. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  5. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  6. 2017Sparsity Invariant CNNscited by 326
  7. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 303
  8. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  9. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  10. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 190
  11. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  12. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 161
22 more
  1. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  2. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  3. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  4. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  5. 2021EagerMOT: 3D Multi-Object Tracking via Sensor Fusioncited by 83
  6. 2019Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagationcited by 74
  7. 2021Weakly Supervised Learning of Rigid 3D Scene Flowcited by 60
  8. 2020Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to Endcited by 55
  9. 2018Confidence Propagation through CNNs for Guided Sparse Depth Regressioncited by 52
  10. 2020Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detectioncited by 37
  11. 2020Reversing the cycle: self-supervised deep stereo through enhanced monocular distillationcited by 34
  12. 2019Noise-Aware Unsupervised Deep Lidar-Stereo Fusioncited by 31
  13. 2021MULLS: Versatile LiDAR SLAM via Multi-metric Linear Least Squarecited by 27
  14. 2017ProbFlow: Joint Optical Flow and Uncertainty Estimationcited by 24
  15. 2019Guided Stereo Matchingcited by 24
  16. 2020DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDARcited by 24
  17. 2020Continual Adaptation for Deep Stereocited by 23
  18. 2021On the confidence of stereo matching in a deep-learning era: a quantitative evaluationcited by 23
  19. 2021A Surface Geometry Model for LiDAR Depth Completioncited by 18
  20. 20193D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalizationcited by 17
  21. 2021S3Net: 3D LiDAR Sparse Semantic Segmentation Networkcited by 9
  22. 2021Sensor-Guided Optical Flowcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 1; 2026: 1.

10 papers.

  1. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusioncited by 50
  2. 2024OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integrationcited by 30
  3. 2023RPEFlow: Multimodal Fusion of RGB-PointCloud-Event for Joint Optical Flow and Scene Flow Estimationcited by 26
  4. 2024OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterationscited by 24
  5. 2023Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalizationcited by 18
  6. 2023Active Stereo Without Pattern Projectorcited by 8
  7. 2025Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Priorcited by 6
  8. 2024Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensorcited by 2
  9. 2024Active Stereo in the Wild through Virtual Pattern Projectioncited by 0
  10. 2026Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusioncited by 0