mlsanityData to 7 Oct 2026

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

arXiv 2310.15171 ↗First posted 23 Oct 2023cs.CV cs.ROcited by 47

Not on the map. Why?

Abstract (arXiv)

Depth estimation from monocular images is pivotal for real-world visual perception systems. While current learning-based depth estimation models train and test on meticulously curated data, they often overlook out-of-distribution (OoD) situations. Yet, in practical settings -- especially safety-critical ones like autonomous driving -- common corruptions can arise. Addressing this oversight, we introduce a comprehensive robustness test suite, RoboDepth, encompassing 18 corruptions spanning three categories: i) weather and lighting conditions; ii) sensor failures and movement; and iii) data processing anomalies. We subsequently benchmark 42 depth estimation models across indoor and outdoor scenes to assess their resilience to these corruptions. Our findings underscore that, in the absence of a dedicated robustness evaluation framework, many leading depth estimation models may be susceptible to typical corruptions. We delve into design considerations for crafting more robust depth estimation models, touching upon pre-training, augmentation, modality, model capacity, and learning paradigms. We anticipate our benchmark will establish a foundational platform for advancing robust OoD depth estimation.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 60 of its 76 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

60 of 76 references.

References · 60

  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  5. 2021Vision Transformers for Dense Predictioncited by 1,789
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  8. 2018Datasheets for Datasetscited by 1,371
  9. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  10. 2019Event-based Vision: A Surveycited by 1,010
  11. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  12. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
38 more
  1. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  2. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  3. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  4. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  5. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  6. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  7. 2017Sparsity Invariant CNNscited by 325
  8. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  9. 2020Robust Consistent Video Depth Estimationcited by 188
  10. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  11. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  12. 2023Robo3D: Towards Robust and Reliable 3D Perception against Corruptionscited by 128
  13. 2019Self-Supervised Monocular Depth Hintscited by 127
  14. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
  15. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  16. 20223D Common Corruptions and Data Augmentationcited by 120
  17. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  18. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  19. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  20. 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
  21. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  22. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  23. 2020A Survey on Deep Learning Techniques for Stereo-based Depth Estimationcited by 90
  24. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  25. 2020Monocular Depth Estimation Based On Deep Learning: An Overviewcited by 68
  26. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  27. 2019Learning monocular depth estimation infusing traditional stereo knowledgecited by 64
  28. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  29. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  30. 2023UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebasecited by 57
  31. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  32. 2021Towards Real-Time Monocular Depth Estimation for Robotics: A Surveycited by 55
  33. 2021SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representationscited by 55
  34. 2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 52
  35. 2022Hierarchical Normalization for Robust Monocular Depth Estimationcited by 51
  36. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 50
  37. 2021When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarkscited by 41
  38. 2020Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applicationscited by 40

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 20; 2025: 13; 2026: 13.

47 papers.

Sort:

By area:

  1. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  2. 2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
  3. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 39
  4. 20244D Contrastive Superflows are Dense 3D Representation Learnerscited by 32
  5. 2024Cross-View Completion Models are Zero-shot Correspondence Estimatorscited by 30
  6. 2024Is Your LiDAR Placement Optimized for 3D Scene Understanding?cited by 25
  7. 2024Multi-Space Alignments Towards Universal LiDAR Segmentationcited by 24
  8. 2025Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimationcited by 20
  9. 2025DepthMaster: Taming Diffusion Models for Monocular Depth Estimationcited by 18
  10. 2024GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistencycited by 17
  11. 2025Perspective-Invariant 3D Object Detectioncited by 16
  12. 2024An Empirical Study of Training State-of-the-Art LiDAR Segmentation Modelscited by 12
35 more
  1. 2025SafeMap: Robust HD Map Construction from Incomplete Observationscited by 12
  2. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  3. 2025LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Drivingcited by 11
  4. 2025Depth Anything at Any Conditioncited by 11
  5. 2025Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representationscited by 7
  6. 2024Scale Propagation Network for Generalizable Depth Completioncited by 5
  7. 2024PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptionscited by 4
  8. 2024Improving Domain Generalization in Self-supervised Monocular Depth Estimation via Stabilized Adversarial Trainingcited by 4
  9. 2025Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbationscited by 4
  10. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  11. 2024A Black-Box Evaluation Framework for Semantic Robustness in Bird's Eye View Detectioncited by 3
  12. 2026Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbationscited by 3
  13. 2024Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectorscited by 2
  14. 2024EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Predictioncited by 2
  15. 2025Vision-based 3D Semantic Scene Completion via Capture Dynamic Representationscited by 2
  16. 2026Faithfulness to Refusal: A Causal Audit of Neuron Selectorscited by 2
  17. 2024Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillationcited by 1
  18. 2026Adapting Depth Anything to Adverse Imaging Conditions with Eventscited by 1
  19. 2026Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesiscited by 1
  20. 2026Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspectivecited by 1
  21. 2024Success Probability in Multi-View Imagingcited by 0
  22. 2024ViewpointDepth: A New Dataset for Monocular Depth Estimation Under Viewpoint Shiftscited by 0
  23. 2024The ADUULM-360 Dataset -- A Multi-Modal Dataset for Depth Estimation in Adverse Weathercited by 0
  24. 2024Multi-Modality Driven LoRA for Adverse Condition Depth Estimationcited by 0
  25. 2025Enhancing Certifiable Semantic Robustness via Robust Pruning of Deep Neural Networkscited by 0
  26. 2025Learning to Navigate Socially Through Proactive Risk Perceptioncited by 0
  27. 2025BoRe-Depth: Self-supervised Monocular Depth Estimation with Boundary Refinement for Embedded Systemscited by 0
  28. 2026RayD3D: Distilling Depth Knowledge Along the Ray for Robust Multi-View 3D Object Detectioncited by 0
  29. 2026x2-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Spacecited by 0
  30. 2026COD10K-C: Benchmarking Robustness of Camouflaged Object Detection Under Natural Image Corruptionscited by 0
  31. 2026Forget, Anticipate and Adapt: Test Time Training for Long Videoscited by 0
  32. 2026Monocular Depth Estimation from a Single Image: Progress and Opportunitiescited by 0
  33. 2026Weather-Conditioned Depth Anythingcited by 0
  34. 2026Robust Multi-Model Fitting through Learning Neighbor Regionscited by 0
  35. 2026AnalogDepth: Multi-view Geometry from FPV drones under Analog Video Transmissioncited by 0