mlsanityData to 14 Oct 2026

FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving

arXiv 2304.10719 ↗First posted 21 Apr 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving. This study proposes a comprehensive self-supervised framework for accurate scale-aware depth prediction on autonomous driving scenes utilizing inter-frame poses obtained from inertial measurements. In particular, we introduce a Full-Scale depth prediction network named FSNet. FSNet contains four important improvements over existing self-supervised models: (1) a multichannel output representation for stable training of depth prediction in driving scenarios, (2) an optical-flow-based mask designed for dynamic object removal, (3) a self-distillation training strategy to augment the training process, and (4) an optimization-based post-processing algorithm in test time, fusing the results from visual odometry. With this framework, robots and vehicles with only one well-calibrated camera can collect sequences of training image frames and camera poses, and infer accurate 3D depths of the environment without extra labeling work or 3D data. Extensive experiments on the KITTI dataset, KITTI-360 dataset and the nuScenes dataset demonstrate the potential of FSNet. More visualizations are presented in urlhttps://sites.google.com/view/fsnet/home

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 21 Apr 2023.

Builds on

30 of 51 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  5. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
  6. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 723
  7. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 575
  8. 2019Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillationcited by 497
  9. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 423
  10. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  11. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  12. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
18 more
  1. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  2. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  3. 2020Regularizing Class-wise Predictions via Self-knowledge Distillationcited by 144
  4. 2019Self-Supervised Monocular Depth Hintscited by 127
  5. 2020Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimationcited by 120
  6. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 110
  7. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  8. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 89
  9. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  10. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  11. 2020MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Cameracited by 59
  12. 2019Ensemble Knowledge Distillation for Learning Improved and Efficient Networkscited by 46
  13. 2021Full Surround Monodepth from Multiple Camerascited by 41
  14. 2020Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applicationscited by 40
  15. 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
  16. 2021GVINS: Tightly Coupled GNSS-Visual-Inertial Fusion for Smooth and Consistent State Estimationcited by 17
  17. 2020Knowledge distillation via adaptive instance normalizationcited by 14
  18. 2021Deterministic Guided LiDAR Depth Map Completioncited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Cameracited by 8
  2. 2025InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformercited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty
  2. 2022SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning
  3. 2023Diffusion-Augmented Depth Prediction with Sparse Annotations
  4. 2022PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes
  5. 2021SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation
  6. 2023Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation
  7. 2022SelfD: Self-Learning Large-Scale Driving Policies From the Web
  8. 2024MAL: Motion-Aware Loss with Temporal and Distillation Hints for Self-Supervised Depth Estimation