mlsanityData to 14 Oct 2026

FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras

arXiv 2205.02930 ↗First posted 5 May 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner. A known issue of self-supervised depth estimation is that it suffers in low-light/over-exposure conditions and in large homogeneous regions. To tackle this issue, we propose a novel ordinal distillation loss that distills the ordinal information from a large teacher model. Such a teacher model, since having been trained on a large amount of diverse data, can capture the depth ordering information well, but lacks in preserving accurate scene geometry. Combined with self-supervised losses, we show that our model can not only generate reasonable depth maps in challenging environments but also better recover the scene geometry. We further leverage the fisheye cameras of an AR-Glasses device to collect an indoor dataset to facilitate evaluation.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 37 of its 42 references that are in the map. First posted on arXiv 5 May 2022.

Builds on

37 of 42 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2021Vision Transformers for Dense Predictioncited by 1,803
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  7. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  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. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
25 more
  1. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 342
  2. 2019Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Videocited by 244
  3. 2020Consistent Video Depth Estimationcited by 220
  4. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  5. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 201
  6. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  7. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  8. 2016Single-Image Depth Perception in the Wildcited by 180
  9. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  10. 2017Learning Depth from Monocular Videos using Direct Methodscited by 154
  11. 2018DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistencycited by 148
  12. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 144
  13. 2019Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Cameracited by 130
  14. 2019Learning the Depths of Moving People by Watching Frozen Peoplecited by 120
  15. 2020ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentationcited by 96
  16. 2018DeepTAM: Deep Tracking and Mappingcited by 87
  17. 2018Learning Monocular Depth by Distilling Cross-domain Stereo Networkscited by 64
  18. 2019Recurrent Neural Network for (Un-)supervised Learning of Monocular VideoVisual Odometry and Depthcited by 50
  19. 2020Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Predictioncited by 41
  20. 2020Learning Monocular Visual Odometry via Self-Supervised Long-Term Modelingcited by 39
  21. 2021MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environmentscited by 38
  22. 2019FisheyeDistanceNet: Self-Supervised Scale-Aware Distance Estimation using Monocular Fisheye Camera for Autonomous Drivingcited by 36
  23. 2020UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Modelscited by 33
  24. 2018Omnidirectional DSO: Direct Sparse Odometry with Fisheye Camerascited by 17
  25. 2022GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mappingcited by 8

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2.

3 papers.

  1. 2023DarSwin: Distortion Aware Radial Swin Transformercited by 10
  2. 2024DarSwin-Unet: Distortion Aware Encoder-Decoder Architecturecited by 1
  3. 2024Uncertainty and Self-Supervision in Single-View Depthcited by 0