mlsanityData to 7 Oct 2026

Bayesian Deep Basis Fitting for Depth Completion with Uncertainty

arXiv 2103.15254 ↗First posted 29 Mar 2021cs.CV cs.ROcited by 23

Not on the map. Why?

Abstract (arXiv)

In this work we investigate the problem of uncertainty estimation for image-guided depth completion. We extend Deep Basis Fitting (DBF) for depth completion within a Bayesian evidence framework to provide calibrated per-pixel variance. The DBF approach frames the depth completion problem in terms of a network that produces a set of low-dimensional depth bases and a differentiable least squares fitting module that computes the basis weights using the sparse depths. By adopting a Bayesian treatment, our Bayesian Deep Basis Fitting (BDBF) approach is able to 1) predict high-quality uncertainty estimates and 2) enable depth completion with few or no sparse measurements. We conduct controlled experiments to compare BDBF against commonly used techniques for uncertainty estimation under various scenarios. Results show that our method produces better uncertainty estimates with accurate depth prediction.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 50 of its 78 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

50 of 78 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  10. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  11. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  12. 2015Weight Uncertainty in Neural Networkscited by 554
38 more
  1. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  2. 2020Virtual KITTI 2cited by 345
  3. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  4. 2017Sparsity Invariant CNNscited by 325
  5. 2015Scalable Bayesian Optimization Using Deep Neural Networkscited by 284
  6. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 227
  7. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  8. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  9. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  10. 2018BA-Net: Dense Bundle Adjustment Networkcited by 173
  11. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  12. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 151
  13. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  14. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  15. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  16. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  17. 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
  18. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  19. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  20. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  21. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  22. 2018The Limits and Potentials of Deep Learning for Roboticscited by 104
  23. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 88
  24. 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
  25. 2018Lightweight Probabilistic Deep Networkscited by 77
  26. 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
  27. 2020Adaptive Context-Aware Multi-Modal Network for Depth Completioncited by 69
  28. 2019Dense Depth Posterior (DDP) from Single Image and Sparse Rangecited by 57
  29. 2020Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to Endcited by 55
  30. 2020TLIO: Tight Learned Inertial Odometrycited by 53
  31. 2018Propagating Confidences through CNNs for Sparse Data Regressioncited by 36
  32. 2019Benchmarking the Neural Linear Model for Regressioncited by 31
  33. 2018Deep Convolutional Compressed Sensing for LiDAR Depth Completioncited by 27
  34. 2019Depth Completion via Deep Basis Fittingcited by 23
  35. 2020CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depthcited by 23
  36. 2020Deep Depth Estimation from Visual-Inertial SLAMcited by 13
  37. 2016Depth Image Inpainting: Improving Low Rank Matrix Completion with Low Gradient Regularizationcited by 11
  38. 2013Expectation Propagation for Neural Networks with Sparsity-promoting Priorscited by 7

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 6; 2023: 4; 2024: 4; 2025: 4.

23 papers.

Sort:

  1. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  2. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
  3. 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
  4. 2024Bilateral Propagation Network for Depth Completioncited by 59
  5. 2022Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objectscited by 49
  6. 2021Learning Topology from Synthetic Data for Unsupervised Depth Completioncited by 38
  7. 2021An Adaptive Framework for Learning Unsupervised Depth Completioncited by 30
  8. 2022DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completioncited by 27
  9. 2024Test-Time Adaptation for Depth Completioncited by 26
  10. 2022Monitored Distillation for Positive Congruent Depth Completioncited by 24
  11. 2022GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNscited by 23
  12. 2023DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstructioncited by 17
11 more
  1. 2023AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimationcited by 15
  2. 2023Estimating 3D Uncertainty Field: Quantifying Uncertainty for Neural Radiance Fieldscited by 14
  3. 2023RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completioncited by 11
  4. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  5. 2021Dense Uncertainty Estimationcited by 9
  6. 2024Sources of Uncertainty in 3D Scene Reconstructioncited by 9
  7. 2024All-day Depth Completioncited by 8
  8. 2025Uncertainty-Aware Autonomous Vehicles: Predicting the Road Aheadcited by 5
  9. 2025ETA: Energy-based Test-time Adaptation for Depth Completioncited by 4
  10. 2022Uncertainty in Real-Time Semantic Segmentation on Embedded Systemscited by 3
  11. 2025PEdger++: Practical Edge Detection via Assembling Cross Informationcited by 0