# Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End

arXiv: https://arxiv.org/abs/2006.03349 · HTML: https://mlsanity.com/paper/2006.03349/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2020.

## Built on by (most cited first, 30 of 55)

- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [Unsupervised Depth Completion with Calibrated Backprojection Layers](https://mlsanity.com/paper/2108.10531/) (2021)
- [LRRU: Long-short Range Recurrent Updating Networks for Depth Completion](https://mlsanity.com/paper/2310.08956/) (2023)
- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [Sparsity Agnostic Depth Completion](https://mlsanity.com/paper/2212.00790/) (2022)
- [Test-Time Adaptation for Depth Completion](https://mlsanity.com/paper/2402.03312/) (2024)
- [Monitored Distillation for Positive Congruent Depth Completion](https://mlsanity.com/paper/2203.16034/) (2022)
- [Bayesian Deep Basis Fitting for Depth Completion with Uncertainty](https://mlsanity.com/paper/2103.15254/) (2021)
- [SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion](https://mlsanity.com/paper/2204.13635/) (2022)
- [A Surface Geometry Model for LiDAR Depth Completion](https://mlsanity.com/paper/2104.08466/) (2021)
- [DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Network](https://mlsanity.com/paper/2108.12655/) (2021)
- [DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction](https://mlsanity.com/paper/2308.15536/) (2023)
- [Uncertainty Quantification Metrics for Deep Regression](https://mlsanity.com/paper/2405.04278/) (2024)
- [AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation](https://mlsanity.com/paper/2310.09739/) (2023)
- [Event Guided Depth Sensing](https://mlsanity.com/paper/2110.10505/) (2021)
- [Learnable Differencing Center for Nighttime Depth Perception](https://mlsanity.com/paper/2306.14538/) (2023)
- [UncAD: Towards Safe End-to-end Autonomous Driving via Online Map Uncertainty](https://mlsanity.com/paper/2504.12826/) (2025)
- [Digging into Depth Priors for Outdoor Neural Radiance Fields](https://mlsanity.com/paper/2308.04413/) (2023)
- [Unsupervised confidence for LiDAR depth maps and applications](https://mlsanity.com/paper/2210.03118/) (2022)
- [RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methods](https://mlsanity.com/paper/2405.10357/) (2024)
- [All-day Depth Completion](https://mlsanity.com/paper/2405.17315/) (2024)
- [DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications](https://mlsanity.com/paper/2406.10068/) (2024)
- [Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN](https://mlsanity.com/paper/2112.04283/) (2021)
- [Learning an Efficient Multimodal Depth Completion Model](https://mlsanity.com/paper/2208.10771/) (2022)
- [MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Report](https://mlsanity.com/paper/2209.07057/) (2022)
- [A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps](https://mlsanity.com/paper/2205.12918/) (2022)
- [3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling](https://mlsanity.com/paper/2209.09231/) (2022)
- [CU-Net: LiDAR Depth-Only Completion With Coupled U-Net](https://mlsanity.com/paper/2210.14898/) (2022)
- [DiffSF: Diffusion Models for Scene Flow Estimation](https://mlsanity.com/paper/2403.05327/) (2024)
- [Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement](https://mlsanity.com/paper/2404.19294/) (2024)

## Abstract (arXiv)

The focus in deep learning research has been mostly to push the limits of prediction accuracy. However, this was often achieved at the cost of increased complexity, raising concerns about the interpretability and the reliability of deep networks. Recently, an increasing attention has been given to untangling the complexity of deep networks and quantifying their uncertainty for different computer vision tasks. Differently, the task of depth completion has not received enough attention despite the inherent noisy nature of depth sensors. In this work, we thus focus on modeling the uncertainty of depth data in depth completion starting from the sparse noisy input all the way to the final prediction. We propose a novel approach to identify disturbed measurements in the input by learning an input confidence estimator in a self-supervised manner based on the normalized convolutional neural networks (NCNNs). Further, we propose a probabilistic version of NCNNs that produces a statistically meaningful uncertainty measure for the final prediction. When we evaluate our approach on the KITTI dataset for depth completion, we outperform all the existing Bayesian Deep Learning approaches in terms of prediction accuracy, quality of the uncertainty measure, and the computational efficiency. Moreover, our small network with 670k parameters performs on-par with conventional approaches with millions of parameters. These results give strong evidence that separating the network into parallel uncertainty and prediction streams leads to state-of-the-art performance with accurate uncertainty estimates.