mlsanityData to 7 Oct 2026

Self-Supervised Depth Completion Guided by 3D Perception and Geometry Consistency

arXiv 2312.15263 ↗First posted 23 Dec 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Depth completion, aiming to predict dense depth maps from sparse depth measurements, plays a crucial role in many computer vision related applications. Deep learning approaches have demonstrated overwhelming success in this task. However, high-precision depth completion without relying on the ground-truth data, which are usually costly, still remains challenging. The reason lies on the ignorance of 3D structural information in most previous unsupervised solutions, causing inaccurate spatial propagation and mixed-depth problems. To alleviate the above challenges, this paper explores the utilization of 3D perceptual features and multi-view geometry consistency to devise a high-precision self-supervised depth completion method. Firstly, a 3D perceptual spatial propagation algorithm is constructed with a point cloud representation and an attention weighting mechanism to capture more reasonable and favorable neighboring features during the iterative depth propagation process. Secondly, the multi-view geometric constraints between adjacent views are explicitly incorporated to guide the optimization of the whole depth completion model in a self-supervised manner. Extensive experiments on benchmark datasets of NYU-Depthv2 and VOID demonstrate that the proposed model achieves the state-of-the-art depth completion performance compared with other unsupervised methods, and competitive performance compared with previous supervised methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 68 references that are in the map. First posted on arXiv 23 Dec 2023.

Builds on

36 of 68 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  6. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  7. 2017Sparsity Invariant CNNscited by 325
  8. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  9. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  10. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  11. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  12. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
24 more
  1. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  2. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  3. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  4. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  5. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  6. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  7. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 88
  8. 2015The Fast Bilateral Solvercited by 86
  9. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  10. 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
  11. 2018Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentationcited by 76
  12. 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
  13. 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
  14. 2019Dense Depth Posterior (DDP) from Single Image and Sparse Rangecited by 57
  15. 2019DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completioncited by 38
  16. 2021Learning Topology from Synthetic Data for Unsupervised Depth Completioncited by 38
  17. 2018Geo-Supervised Visual Depth Predictioncited by 33
  18. 2018HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completioncited by 32
  19. 2021An Adaptive Framework for Learning Unsupervised Depth Completioncited by 30
  20. 2020Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Datacited by 28
  21. 2018Deep Convolutional Compressed Sensing for LiDAR Depth Completioncited by 27
  22. 2022Monitored Distillation for Positive Congruent Depth Completioncited by 24
  23. 2020DepthNet: Real-Time LiDAR Point Cloud Depth Completion for Autonomous Vehiclescited by 11
  24. 2023Virtual Reality Sickness Reduces Attention During Immersive Experiencescited by 1

Built on by

Not cited yet.