mlsanityData to 7 Oct 2026

Revisiting Self-Supervised Monocular Depth Estimation

arXiv 2103.12496 ↗First posted 23 Mar 2021cs.CV cs.AI cs.ROcited by 2

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning of depth map prediction and motion estimation from monocular video sequences is of vital importance -- since it realizes a broad range of tasks in robotics and autonomous vehicles. A large number of research efforts have enhanced the performance by tackling illumination variation, occlusions, and dynamic objects, to name a few. However, each of those efforts targets individual goals and endures as separate works. Moreover, most of previous works have adopted the same CNN architecture, not reaping architectural benefits. Therefore, the need to investigate the inter-dependency of the previous methods and the effect of architectural factors remains. To achieve these objectives, we revisit numerous previously proposed self-supervised methods for joint learning of depth and motion, perform a comprehensive empirical study, and unveil multiple crucial insights. Furthermore, we remarkably enhance the performance as a result of our study -- outperforming previous state-of-the-art performance.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 45 of its 60 references that are in the map. First posted on arXiv 23 Mar 2021.

Builds on

45 of 60 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  8. 2014Going Deeper with Convolutionscited by 4,231
  9. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  11. 2019Searching for MobileNetV3cited by 1,984
  12. 2017Deformable Convolutional Networkscited by 1,481
33 more
  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  2. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  3. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  6. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  7. 2018Do Better ImageNet Models Transfer Better?cited by 560
  8. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  9. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  10. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 340
  11. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  12. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  13. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  14. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
  15. 2018Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraintscited by 179
  16. 2019Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Camerascited by 170
  17. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  18. 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
  19. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  20. 2018NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applicationscited by 146
  21. 2018Evaluating Bayesian Deep Learning Methods for Semantic Segmentationcited by 143
  22. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  23. 2019Learning the Depths of Moving People by Watching Frozen Peoplecited by 120
  24. 2014Neural Variational Inference and Learning in Belief Networkscited by 116
  25. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  26. 2016Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothnesscited by 101
  27. 2018Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understandingcited by 101
  28. 2020Unsupervised Monocular Depth Learning in Dynamic Scenescited by 84
  29. 2018The Description Length of Deep Learning Modelscited by 71
  30. 2017Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Camerascited by 45
  31. 2018Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priorscited by 35
  32. 2018SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perceptioncited by 16
  33. 2019SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

2 papers.

  1. 2021Dimensions of Motion: Monocular Prediction through Flow Subspacescited by 10
  2. 2026Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictionscited by 1