mlsanityData to 14 Oct 2026

SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes

arXiv 2211.03660 ↗First posted 7 Nov 2022cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries because they are usually occluded in other training views. In this paper, we propose SC-DepthV3 for addressing the challenges. Specifically, we introduce an external pretrained monocular depth estimation model for generating single-image depth prior, namely pseudo-depth, based on which we propose novel losses to boost self-supervised training. As a result, our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes. We demonstrate the significantly superior performance of our method over previous methods on six challenging datasets, and we provide detailed ablation studies for the proposed terms. Source code and data will be released at https://github.com/JiawangBian/sc_depth_pl

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 49 of its 75 references that are in the map. First posted on arXiv 7 Nov 2022.

Builds on

49 of 75 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021Vision Transformers for Dense Predictioncited by 1,803
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  7. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  8. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  9. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  10. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  11. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  12. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
37 more
  1. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  2. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  3. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
  4. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  5. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  6. 2020Consistent Video Depth Estimationcited by 220
  7. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  8. 2019ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residualscited by 181
  9. 2016Single-Image Depth Perception in the Wildcited by 180
  10. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  11. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  12. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  13. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  14. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  15. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  16. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  17. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  18. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  19. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
  20. 2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
  21. 2019Learning the Depths of Moving People by Watching Frozen Peoplecited by 120
  22. 2020Towards Better Generalization: Joint Depth-Pose Learning without PoseNetcited by 85
  23. 2020Unsupervised Monocular Depth Learning in Dynamic Scenescited by 84
  24. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  25. 2020RGB-D Salient Object Detection: A Surveycited by 73
  26. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  27. 2019DepthTransfer: Depth Extraction from Video Using Non-parametric Samplingcited by 60
  28. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  29. 2019Visual Odometry Revisited: What Should Be Learnt?cited by 57
  30. 2022Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depthcited by 48
  31. 2020P2Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimationcited by 41
  32. 2020Auto-Rectify Network for Unsupervised Indoor Depth Estimationcited by 39
  33. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  34. 2022PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planescited by 32
  35. 2019Moving Indoor: Unsupervised Video Depth Learning in Challenging Environmentscited by 31
  36. 2018Learning Single-Image Depth from Videos using Quality Assessment Networkscited by 25
  37. 2016Depth from a Single Image by Harmonizing Overcomplete Local Network Predictionscited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 16; 2025: 20; 2026: 7.

52 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  2. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  3. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  4. 2023RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptionscited by 49
  5. 2024EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Cameracited by 43
  6. 2024SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splattingcited by 42
  7. 2024MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Viewscited by 29
  8. 2025Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priorscited by 22
  9. 2023Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenescited by 20
  10. 2023FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Modelscited by 17
  11. 2024Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Surveycited by 15
  12. 2023The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimationcited by 13
38 more
  1. 2024DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimationcited by 13
  2. 2024Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoningcited by 12
  3. 2025Revisiting Depth Representations for Feed-Forward 3D Gaussian Splattingcited by 12
  4. 2025Depth Anything at Any Conditioncited by 12
  5. 2024FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Cameracited by 8
  6. 2024ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Predictioncited by 8
  7. 2024SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learningcited by 7
  8. 2023NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimationcited by 6
  9. 2025Always Clear Depth: Robust Monocular Depth Estimation under Adverse Weathercited by 6
  10. 2025SAB3R: Semantic-Augmented Backbone in 3D Reconstructioncited by 6
  11. 2025StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimationcited by 6
  12. 2024DepthMOT: Depth Cues Lead to a Strong Multi-Object Trackercited by 5
  13. 20253D Scene Understanding Through Local Random Access Sequence Modelingcited by 5
  14. 2023MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimationcited by 4
  15. 2025ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimationcited by 4
  16. 2024GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraintscited by 3
  17. 2025G3Splat: Geometrically Consistent Generalizable Gaussian Splattingcited by 3
  18. 2024Structure-Centric Robust Monocular Depth Estimation via Knowledge Distillationcited by 2
  19. 2025UNO: Unified Self-Supervised Monocular Odometry for Platform-Agnostic Deploymentcited by 2
  20. 2025Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Millisecondscited by 2
  21. 2024Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometrycited by 1
  22. 2024Self-supervised Pretraining and Finetuning for Monocular Depth and Visual Odometrycited by 1
  23. 2025An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open Worldcited by 1
  24. 2025Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learningcited by 1
  25. 2026GPA-VGGT:Adapting VGGT to Large Scale Localization by Self-Supervised Learning with Geometry and Physics Aware Losscited by 1
  26. 2023Federated Self-Supervised Learning of Monocular Depth Estimators for Autonomous Vehiclescited by 0
  27. 2024FA-Depth: Toward Fast and Accurate Self-supervised Monocular Depth Estimationcited by 0
  28. 2025Monocular Depth Guided Occlusion-Aware Disparity Refinement via Semi-supervised Learning in Laparoscopic Imagescited by 0
  29. 2025Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matchingcited by 0
  30. 2025Self-Supervised Learning to Fly using Efficient Semantic Segmentation and Metric Depth Estimation for Low-Cost Autonomous UAVscited by 0
  31. 2025EndoSfM3D: Learning to 3D Reconstruct Any Endoscopic Surgery Scene using Self-supervised Foundation Modelcited by 0
  32. 2025BoRe-Depth: Self-supervised Monocular Depth Estimation with Boundary Refinement for Embedded Systemscited by 0
  33. 2025Accuracy Does Not Guarantee Human-Likeness: Cross-Domain Human-Centered Benchmark in Monocular Depth Estimationcited by 0
  34. 2025DASP: Self-supervised Nighttime Monocular Depth Estimation with Domain Adaptation of Spatiotemporal Priorscited by 0
  35. 2026CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimationcited by 0
  36. 2026Binarized High-Efficiency RAW Video Restoration and Beyondcited by 0
  37. 2026Monocular Depth Estimation from a Single Image: Progress and Opportunitiescited by 0
  38. 2026CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attentioncited by 0

50 most cited of 52 All 52 (JSON)