mlsanityData to 7 Oct 2026

DVMN: Dense Validity Mask Network for Depth Completion

arXiv 2107.06709 ↗First posted 14 Jul 2021cs.CV eess.IVcited by 3

Not on the map. Why?

Abstract (arXiv)

LiDAR depth maps provide environmental guidance in a variety of applications. However, such depth maps are typically sparse and insufficient for complex tasks such as autonomous navigation. State of the art methods use image guided neural networks for dense depth completion. We develop a guided convolutional neural network focusing on gathering dense and valid information from sparse depth maps. To this end, we introduce a novel layer with spatially variant and content-depended dilation to include additional data from sparse input. Furthermore, we propose a sparsity invariant residual bottleneck block. We evaluate our Dense Validity Mask Network (DVMN) on the KITTI depth completion benchmark and achieve state of the art results. At the time of submission, our network is the leading method using sparsity invariant convolution.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 38 references that are in the map. First posted on arXiv 14 Jul 2021.

Builds on

34 of 38 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  4. 2016Pyramid Scene Parsing Networkcited by 2,472
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  6. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  7. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  8. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  9. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  10. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  11. 2019Selective Kernel Networkscited by 401
  12. 2017Sparsity Invariant CNNscited by 325
22 more
  1. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  2. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  3. 2017Understanding Convolution for Semantic Segmentationcited by 168
  4. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  5. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  6. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  7. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  8. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  9. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  10. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  11. 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
  12. 2018Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentationcited by 76
  13. 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
  14. 2020Adaptive Context-Aware Multi-Modal Network for Depth Completioncited by 69
  15. 2018Confidence Propagation through CNNs for Guided Sparse Depth Regressioncited by 52
  16. 2019DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completioncited by 38
  17. 2018Propagating Confidences through CNNs for Sparse Data Regressioncited by 36
  18. 2020Deformable spatial propagation network for depth completioncited by 30
  19. 2018Deep Convolutional Compressed Sensing for LiDAR Depth Completioncited by 27
  20. 2020DeepLiDARFlow: A Deep Learning Architecture For Scene Flow Estimation Using Monocular Camera and Sparse LiDARcited by 24
  21. 2019SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Taskscited by 13
  22. 2020SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolationcited by 12

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 1.

3 papers.

  1. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  2. 2024RadarPillars: Efficient Object Detection from 4D Radar Point Cloudscited by 23
  3. 2023360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentationcited by 12