mlsanityData to 14 Oct 2026

Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes

arXiv 2310.18887 ↗First posted 29 Oct 2023cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

Unsupervised monocular depth estimation techniques have demonstrated encouraging results but typically assume that the scene is static. These techniques suffer when trained on dynamical scenes, where apparent object motion can equally be explained by hypothesizing the object's independent motion, or by altering its depth. This ambiguity causes depth estimators to predict erroneous depth for moving objects. To resolve this issue, we introduce Dynamo-Depth, an unifying approach that disambiguates dynamical motion by jointly learning monocular depth, 3D independent flow field, and motion segmentation from unlabeled monocular videos. Specifically, we offer our key insight that a good initial estimation of motion segmentation is sufficient for jointly learning depth and independent motion despite the fundamental underlying ambiguity. Our proposed method achieves state-of-the-art performance on monocular depth estimation on Waymo Open and nuScenes Dataset with significant improvement in the depth of moving objects. Code and additional results are available at https://dynamo-depth.github.io.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 41 of its 49 references that are in the map. First posted on arXiv 29 Oct 2023.

Builds on

41 of 49 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  6. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  7. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
  8. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  9. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  10. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  11. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  12. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
29 more
  1. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  2. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  3. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  4. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  5. 2020Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidancecited by 148
  6. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 118
  7. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  8. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  9. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  10. 2017SfM-Net: Learning of Structure and Motion from Videocited by 89
  11. 2020Towards Better Generalization: Joint Depth-Pose Learning without PoseNetcited by 85
  12. 2020Unsupervised Monocular Depth Learning in Dynamic Scenescited by 84
  13. 2020Self-Supervised Monocular Scene Flow Estimationcited by 64
  14. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  15. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 58
  16. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 52
  17. 2021Learning to Segment Rigid Motions from Two Framescited by 46
  18. 2021R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenescited by 36
  19. 2021PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation with Neural Positional Encoding and Distilled Matting Losscited by 31
  20. 2022Learning Optical Flow, Depth, and Scene Flow without Real-World Labelscited by 31
  21. 2021Self-Supervised Multi-Frame Monocular Scene Flowcited by 29
  22. 2021Attentive and Contrastive Learning for Joint Depth and Motion Field Estimationcited by 24
  23. 2022When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimationcited by 24
  24. 2020EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentationcited by 22
  25. 2023RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenescited by 22
  26. 2022Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamicscited by 20
  27. 2022Instance-aware multi-object self-supervision for monocular depth predictioncited by 5
  28. 2022Dyna-DM: Dynamic Object-aware Self-supervised Monocular Depth Mapscited by 3
  29. 2023Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenescited by 2

Built on by

Cited by year (2026 to 14 Oct)

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

20 papers.

Sort:

By area:

  1. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 47
  2. 2024VDG: Vision-Only Dynamic Gaussian for Driving Simulationcited by 16
  3. 2024DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimationcited by 13
  4. 2024EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splattingcited by 13
  5. 2025Feed-Forward SceneDINO for Unsupervised Semantic Scene Completioncited by 13
  6. 2023Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenescited by 12
  7. 2024ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Predictioncited by 8
  8. 2024SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learningcited by 7
  9. 2024ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusioncited by 6
  10. 2024Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimationcited by 3
  11. 2024On-Device Self-Supervised Learning of Low-Latency Monocular Depth from Only Eventscited by 3
  12. 2024MOD-UV: Learning Mobile Object Detectors from Unlabeled Videoscited by 2
8 more
  1. 2024Human Insights Driven Latent Space for Different Driving Perspectives: A Unified Encoder for Efficient Multi-Task Inferencecited by 1
  2. 2025Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learningcited by 1
  3. 2026Scene-Centric Unsupervised Video Panoptic Segmentationcited by 1
  4. 2025Enhancing Steering Estimation with Semantic-Aware GNNscited by 0
  5. 2025BoRe-Depth: Self-supervised Monocular Depth Estimation with Boundary Refinement for Embedded Systemscited by 0
  6. 2026SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulationcited by 0
  7. 2026Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimationcited by 0
  8. 2026Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Drivingcited by 0