mlsanityData to 7 Oct 2026

Gradient-based Uncertainty for Monocular Depth Estimation

arXiv 2208.02005 ↗First posted 3 Aug 2022cs.CVcited by 26

Not on the map. Why?

Abstract (arXiv)

In monocular depth estimation, disturbances in the image context, like moving objects or reflecting materials, can easily lead to erroneous predictions. For that reason, uncertainty estimates for each pixel are necessary, in particular for safety-critical applications such as automated driving. We propose a post hoc uncertainty estimation approach for an already trained and thus fixed depth estimation model, represented by a deep neural network. The uncertainty is estimated with the gradients which are extracted with an auxiliary loss function. To avoid relying on ground-truth information for the loss definition, we present an auxiliary loss function based on the correspondence of the depth prediction for an image and its horizontally flipped counterpart. Our approach achieves state-of-the-art uncertainty estimation results on the KITTI and NYU Depth V2 benchmarks without the need to retrain the neural network. Models and code are publicly available at https://github.com/jhornauer/GrUMoDepth.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 27 of its 32 references that are in the map. First posted on arXiv 3 Aug 2022.

Builds on

27 of 32 references.

References · 27

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  5. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  6. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  7. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  8. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  9. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  10. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  11. 2017Sparsity Invariant CNNscited by 325
  12. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
15 more
  1. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  2. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  3. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  4. 2018Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flowcited by 135
  5. 2018Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometrycited by 85
  6. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  7. 2019Learning monocular depth estimation infusing traditional stereo knowledgecited by 64
  8. 2020Gradients as a Measure of Uncertainty in Neural Networkscited by 55
  9. 2018Classification Uncertainty of Deep Neural Networks Based on Gradient Informationcited by 43
  10. 2019Training-Free Uncertainty Estimation for Dense Regression: Sensitivity as a Surrogatecited by 28
  11. 2017ProbFlow: Joint Optical Flow and Uncertainty Estimationcited by 24
  12. 2021CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameterscited by 8
  13. 2021SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimationcited by 7
  14. 2021NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesiscited by 7
  15. 2019Region Deformer Networks for Unsupervised Depth Estimation from Unconstrained Monocular Videoscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 8; 2025: 4; 2026: 2.

26 papers.

Sort:

By area:

  1. 2024NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wildcited by 85
  2. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  3. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditionscited by 29
  4. 2023POCO: 3D Pose and Shape Estimation with Confidencecited by 20
  5. 2025Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splattingcited by 20
  6. 2024RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Lossescited by 18
  7. 2024Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimationcited by 17
  8. 2022ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inferencecited by 15
  9. 2023Single Image Depth Prediction Made Better: A Multivariate Gaussian Takecited by 14
  10. 2023Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentationcited by 11
  11. 2023Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Imagescited by 8
  12. 2023ProbVLM: Probabilistic Adapter for Frozen Vision-Language Modelscited by 7
14 more
  1. 2023Out-of-Distribution Detection for Monocular Depth Estimationcited by 7
  2. 2023Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regressioncited by 7
  3. 2025Revisiting Gradient-based Uncertainty for Monocular Depth Estimationcited by 5
  4. 2023Robust Self-Supervised Extrinsic Self-Calibrationcited by 4
  5. 2024Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstructioncited by 3
  6. 2023ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimationcited by 2
  7. 2025A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimationcited by 2
  8. 2023Measuring and Modeling Uncertainty Degree for Monocular Depth Estimationcited by 1
  9. 2023FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stackcited by 1
  10. 2024Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimationcited by 1
  11. 2024Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matchingcited by 1
  12. 2025Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shiftscited by 1
  13. 2026Robust Uncertainty Estimation under Distribution Shift via Difference Reconstructioncited by 0
  14. 2026A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Modelscited by 0