mlsanityData to 7 Oct 2026

Deep Depth Completion from Extremely Sparse Data: A Survey

arXiv 2205.05335 ↗First posted 11 May 2022cs.CVcited by 33

Not on the map. Why?

Abstract (arXiv)

Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e.g., LiDARs. It plays an essential role in various applications such as autonomous driving, 3D reconstruction, augmented reality, and robot navigation. Recent successes on the task have been demonstrated and dominated by deep learning based solutions. In this article, for the first time, we provide a comprehensive literature review that helps readers better grasp the research trends and clearly understand the current advances. We investigate the related studies from the design aspects of network architectures, loss functions, benchmark datasets, and learning strategies with a proposal of a novel taxonomy that categorizes existing methods. Besides, we present a quantitative comparison of model performance on three widely used benchmarks, including indoor and outdoor datasets. Finally, we discuss the challenges of prior works and provide readers with some insights for future research directions.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 90 of its 154 references that are in the map. First posted on arXiv 11 May 2022.

Builds on

90 of 154 references.

References · 90

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  10. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  11. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  12. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
38 more
  1. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  2. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  3. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  4. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 583
  5. 2018Conditional Neural Processescited by 421
  6. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  7. 2019Dynamic Convolution: Attention over Convolution Kernelscited by 355
  8. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  9. 2017Sparsity Invariant CNNscited by 325
  10. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 233
  11. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
  12. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  13. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  14. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  15. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  16. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 144
  17. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  18. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  19. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  20. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  21. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  22. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  23. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  24. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  25. 2019FastDepth: Fast Monocular Depth Estimation on Embedded Systemscited by 93
  26. 2016Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networkscited by 91
  27. 2019Unsupervised Depth Completion from Visual Inertial Odometrycited by 88
  28. 2019How do neural networks see depth in single images?cited by 82
  29. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  30. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  31. 2019Sparse and noisy LiDAR completion with RGB guidance and uncertaintycited by 79
  32. 2018Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentationcited by 76
  33. 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
  34. 2022Dynamic Spatial Propagation Network for Depth Completioncited by 70
  35. 2020Adaptive Context-Aware Multi-Modal Network for Depth Completioncited by 69
  36. 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
  37. 2019Dense Depth Posterior (DDP) from Single Image and Sparse Rangecited by 57
  38. 2020Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to Endcited by 55

50 most cited of 90 All 90 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 10; 2025: 5; 2026: 8.

33 papers.

Sort:

By area:

  1. 2023Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Taskscited by 41
  2. 2024HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptionscited by 24
  3. 2023Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalizationcited by 18
  4. 2023Learnable Differencing Center for Nighttime Depth Perceptioncited by 14
  5. 2025Distilling Monocular Foundation Model for Fine-grained Depth Completioncited by 14
  6. 2024HGS-Mapping: Online Dense Mapping Using Hybrid Gaussian Representation in Urban Scenescited by 11
  7. 2023Video Frame Interpolation with Stereo Event and Intensity Cameracited by 10
  8. 2023EVI-SAM: Robust, Real-time, Tightly-coupled Event-Visual-Inertial State Estimation and 3D Dense Mappingcited by 9
  9. 2023Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater Robotscited by 8
  10. 2023SparseDC: Depth Completion from sparse and non-uniform inputscited by 8
  11. 2024RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methodscited by 8
  12. 2024Scale Propagation Network for Generalizable Depth Completioncited by 5
21 more
  1. 2022Dense Depth Distillation with Out-of-Distribution Simulated Imagescited by 4
  2. 2024CFPNet: Improving Lightweight ToF Depth Completion via Cross-zone Feature Propagationcited by 4
  3. 2023Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimationcited by 2
  4. 2024Depth on Demand: Streaming Dense Depth from a Low Frame Rate Active Sensorcited by 2
  5. 2026TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Imagecited by 2
  6. 2024A Concise but High-performing Network for Image Guided Depth Completion in Autonomous Drivingcited by 1
  7. 2024VIRUS-NeRF -- Vision, InfraRed and UltraSonic based Neural Radiance Fieldscited by 1
  8. 2024A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completioncited by 1
  9. 2025REOcc: Camera-Radar Fusion with Radar Feature Enrichment for 3D Occupancy Predictioncited by 1
  10. 2026DAWN: Noise-Robust Quadruped Parkour via Depth-Denoising World Modelscited by 1
  11. 2023Sparse Depth-Guided Attention for Accurate Depth Completion: A Stereo-Assisted Monitored Distillation Approachcited by 0
  12. 2024WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model Researchcited by 0
  13. 2025Real-World Depth Recovery via Structure Uncertainty Modeling and Inaccurate GT Depth Fittingcited by 0
  14. 2025Skeleton-based Robust Registration Framework for Corrupted 3D Point Cloudscited by 0
  15. 2025Geometry-Aware Sparse Depth Sampling for High-Fidelity RGB-D Depth Completion in Robotic Systemscited by 0
  16. 2026Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmissioncited by 0
  17. 2026Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusioncited by 0
  18. 2026NavTrust: Benchmarking Trustworthiness for Embodied Navigationcited by 0
  19. 2026ToFormer: Towards Large-scale Scenario Depth Completion for Lightweight ToF Cameracited by 0
  20. 2026EfficientPENet: Real-Time Depth Completion from Sparse LiDAR via Lightweight Multi-Modal Fusioncited by 0
  21. 2026Decoupling Ego-Motion from Target Dynamics via Dual-Interval Motion Cues for UAV Detectioncited by 0