mlsanityData to 7 Oct 2026

Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement

arXiv 2404.19294 ↗First posted 30 Apr 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

The main function of depth completion is to compensate for an insufficient and unpredictable number of sparse depth measurements of hardware sensors. However, existing research on depth completion assumes that the sparsity -- the number of points or LiDAR lines -- is fixed for training and testing. Hence, the completion performance drops severely when the number of sparse depths changes significantly. To address this issue, we propose the sparsity-adaptive depth refinement (SDR) framework, which refines monocular depth estimates using sparse depth points. For SDR, we propose the masked spatial propagation network (MSPN) to perform SDR with a varying number of sparse depths effectively by gradually propagating sparse depth information throughout the entire depth map. Experimental results demonstrate that MPSN achieves state-of-the-art performance on both SDR and conventional depth completion scenarios.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 61 of its 78 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

61 of 78 references.

References · 61

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2020End-to-End Object Detection with Transformerscited by 7,384
  7. 2016Layer Normalizationcited by 5,579
  8. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  9. 2021Vision Transformers for Dense Predictioncited by 1,789
  10. 2017Deformable Convolutional Networkscited by 1,481
  11. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  12. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
38 more
  1. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  2. 2022Simple Baselines for Image Restorationcited by 701
  3. 2021Perceiver IO: A General Architecture for Structured Inputs & Outputscited by 616
  4. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  5. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  6. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  7. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  8. 2022Neighborhood Attention Transformercited by 235
  9. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  10. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  11. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  12. 2016Single-Image Depth Perception in the Wildcited by 179
  13. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  14. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  15. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 144
  16. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  17. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  18. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  19. 2021RegionViT: Regional-to-Local Attention for Vision Transformerscited by 126
  20. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  21. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  22. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  23. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  24. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  25. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 92
  26. 2020Guiding Monocular Depth Estimation Using Depth-Attention Volumecited by 82
  27. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  28. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  29. 2016IM2CADcited by 78
  30. 2018PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Imagecited by 77
  31. 2017Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimationcited by 70
  32. 2022Dynamic Spatial Propagation Network for Depth Completioncited by 70
  33. 2020Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to Endcited by 55
  34. 2018Confidence Propagation through CNNs for Guided Sparse Depth Regressioncited by 52
  35. 2019Structure-Aware Residual Pyramid Network for Monocular Depth Estimationcited by 49
  36. 2021MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokenscited by 46
  37. 2020FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completioncited by 45
  38. 2019Depth Coefficients for Depth Completioncited by 41

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2026Any to Full: Prompting Depth Anything for Depth Completion in One Stagecited by 5
  2. 2025DEPTHOR: Depth Enhancement from a Practical Light-Weight dToF Sensor and RGB Imagecited by 3
  3. 2025Perfecting Depth: Uncertainty-Aware Enhancement of Metric Depthcited by 1
  4. 2025DEPTHOR++: Robust Depth Enhancement from a Real-World Lightweight dToF and RGB Guidancecited by 1
  5. 2025Geometry-Aware Sparse Depth Sampling for High-Fidelity RGB-D Depth Completion in Robotic Systemscited by 0