mlsanityData to 7 Oct 2026

Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth

arXiv 2203.15174 ↗First posted 29 Mar 2022cs.CV cs.AI cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions. Existing dynamic-object-focused methods only partially solved the mismatch problem at the training loss level. In this paper, we accordingly propose a novel multi-frame monocular depth prediction method to solve these problems at both the prediction and supervision loss levels. Our method, called DynamicDepth, is a new framework trained via a self-supervised cycle consistent learning scheme. A Dynamic Object Motion Disentanglement (DOMD) module is proposed to disentangle object motions to solve the mismatch problem. Moreover, novel occlusion-aware Cost Volume and Re-projection Loss are designed to alleviate the occlusion effects of object motions. Extensive analyses and experiments on the Cityscapes and KITTI datasets show that our method significantly outperforms the state-of-the-art monocular depth prediction methods, especially in the areas of dynamic objects. Code is available at https://github.com/AutoAILab/DynamicDepth

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). Builds on 48 of its 56 references that are in the map. First posted on arXiv 29 Mar 2022.

Builds on

48 of 56 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  6. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  7. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  8. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  9. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  10. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  11. 2017Sparsity Invariant CNNscited by 325
  12. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
36 more
  1. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  2. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  3. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  4. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  5. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  6. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  7. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  8. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  9. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  10. 2020Semantically-Guided Representation Learning for Self-Supervised Monocular Depthcited by 134
  11. 2019Self-Supervised Monocular Depth Hintscited by 127
  12. 2019Learning the Depths of Moving People by Watching Frozen Peoplecited by 120
  13. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  14. 2020EfficientPS: Efficient Panoptic Segmentationcited by 111
  15. 2017Semi-Supervised Deep Learning for Monocular Depth Map Predictioncited by 109
  16. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  17. 2017UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learningcited by 95
  18. 2020Unsupervised Monocular Depth Learning in Dynamic Scenescited by 84
  19. 2020Don't Forget The Past: Recurrent Depth Estimation from Monocular Videocited by 71
  20. 2018SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimationcited by 64
  21. 2019Learning monocular depth estimation infusing traditional stereo knowledgecited by 64
  22. 2019Exploiting temporal consistency for real-time video depth estimationcited by 61
  23. 2020MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Cameracited by 59
  24. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  25. 2019Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depthcited by 50
  26. 2019Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semanticscited by 49
  27. 2018LEGO: Learning Edge with Geometry all at Once by Watching Videoscited by 47
  28. 2018Unsupervised Adversarial Depth Estimation using Cycled Generative Networkscited by 45
  29. 2020Single Image Depth Estimation Trained via Depth from Defocus Cuescited by 45
  30. 2019Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Predictioncited by 44
  31. 2018Learning monocular depth estimation with unsupervised trinocular assumptionscited by 36
  32. 2019Unsupervised High-Resolution Depth Learning From Videos With Dual Networkscited by 26
  33. 2021Attentive and Contrastive Learning for Joint Depth and Motion Field Estimationcited by 24
  34. 2020Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cuescited by 19
  35. 2018SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perceptioncited by 16
  36. 2020Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 13; 2024: 19; 2025: 10; 2026: 3.

48 papers.

Sort:

By area:

  1. 2025Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awarenesscited by 61
  2. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 50
  3. 2023TransFlow: Transformer as Flow Learnercited by 32
  4. 2025WonderTurbo: Generating Interactive 3D World in 0.72 Secondscited by 31
  5. 2024Cross-View Completion Models are Zero-shot Correspondence Estimatorscited by 30
  6. 2024NARUTO: Neural Active Reconstruction from Uncertain Target Observationscited by 27
  7. 2023Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Modelscited by 26
  8. 2023Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenescited by 25
  9. 2025Back on Track: Bundle Adjustment for Dynamic Scene Reconstructioncited by 23
  10. 2023SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimationcited by 21
  11. 2025Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimationcited by 20
  12. 2025Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priorscited by 20
36 more
  1. 2023CVRecon: Rethinking 3D Geometric Feature Learning For Neural Reconstructioncited by 16
  2. 2023From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Priorcited by 13
  3. 2024SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Imagescited by 13
  4. 2022Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learningcited by 12
  5. 2023Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenescited by 12
  6. 2024Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoningcited by 12
  7. 2024DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimationcited by 12
  8. 2024M2Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimationcited by 10
  9. 2022D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidancecited by 9
  10. 2024Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimationcited by 9
  11. 2023DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volumecited by 8
  12. 2024SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimationcited by 8
  13. 2024SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learningcited by 7
  14. 2024Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Modelscited by 6
  15. 2024ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusioncited by 6
  16. 2025Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimationcited by 6
  17. 2024MAL: Motion-Aware Loss with Temporal and Distillation Hints for Self-Supervised Depth Estimationcited by 4
  18. 2024MambaDepth: Enhancing Long-range Dependency for Self-Supervised Fine-Structured Monocular Depth Estimationcited by 4
  19. 2023PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimationcited by 3
  20. 2024SAM-Guided Masked Token Prediction for 3D Scene Understandingcited by 3
  21. 2023Multi-Frame Self-Supervised Depth Estimation with Multi-Scale Feature Fusion in Dynamic Scenescited by 2
  22. 2024FlowDepth: Decoupling Optical Flow for Self-Supervised Monocular Depth Estimationcited by 2
  23. 2024BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimationcited by 2
  24. 2024High-Precision Self-Supervised Monocular Depth Estimation with Rich-Resource Priorcited by 2
  25. 2023GSDC Transformer: An Efficient and Effective Cue Fusion for Monocular Multi-Frame Depth Estimationcited by 1
  26. 2024Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inferencecited by 1
  27. 2025CoProU-VO: Combining Projected Uncertainty for End-to-End Unsupervised Monocular Visual Odometrycited by 1
  28. 2026Scene-Centric Unsupervised Video Panoptic Segmentationcited by 1
  29. 2023Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimationcited by 0
  30. 2023Learning Monocular Depth in Dynamic Environment via Context-aware Temporal Attentioncited by 0
  31. 2024PhysDepth: Plug-and-Play Physical Refinement for Monocular Depth Estimation in Challenging Environmentscited by 0
  32. 2025DSOcc: Leveraging Depth Awareness and Semantic Aid to Boost Camera-Based 3D Semantic Occupancy Predictioncited by 0
  33. 2025UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometrycited by 0
  34. 2025DASP: Self-supervised Nighttime Monocular Depth Estimation with Domain Adaptation of Spatiotemporal Priorscited by 0
  35. 2026Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimationcited by 0
  36. 2026Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Drivingcited by 0