mlsanityData to 14 Oct 2026

Towards Domain-agnostic Depth Completion

arXiv 2207.14466 ↗First posted 29 Jul 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task domains. We present a method to complete sparse/semi-dense, noisy, and potentially low-resolution depth maps obtained by various range sensors, including those in modern mobile phones, or by multi-view reconstruction algorithms. Our method leverages a data-driven prior in the form of a single image depth prediction network trained on large-scale datasets, the output of which is used as an input to our model. We propose an effective training scheme where we simulate various sparsity patterns in typical task domains. In addition, we design two new benchmarks to evaluate the generalizability and the robustness of depth completion methods. Our simple method shows superior cross-domain generalization ability against state-of-the-art depth completion methods, introducing a practical solution to high-quality depth capture on a mobile device. The code is available at: https://github.com/YvanYin/FillDepth.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 43 of its 67 references that are in the map. First posted on arXiv 29 Jul 2022.

Builds on

43 of 67 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  4. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  7. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  8. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  9. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  10. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  11. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  12. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
31 more
  1. 2017Sparsity Invariant CNNscited by 326
  2. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 244
  3. 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 240
  4. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  5. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  6. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 195
  7. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  8. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 161
  9. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 136
  10. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  11. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  12. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  13. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 110
  14. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  15. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  16. 2020Efficient RGB-D Semantic Segmentation for Indoor Scene Analysiscited by 84
  17. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  18. 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
  19. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  20. 2020DiverseDepth: Affine-invariant Depth Prediction Using Diverse Datacited by 61
  21. 2019Dense Depth Posterior (DDP) from Single Image and Sparse Rangecited by 57
  22. 2019Learning Single Camera Depth Estimation using Dual-Pixelscited by 49
  23. 2019DeceptionNet: Network-Driven Domain Randomizationcited by 43
  24. 2019Depth Coefficients for Depth Completioncited by 41
  25. 2021Depth Completion with Twin Surface Extrapolation at Occlusion Boundariescited by 41
  26. 2017Domain Randomization and Generative Models for Robotic Graspingcited by 36
  27. 2019Indoor Depth Completion with Boundary Consistency and Self-Attentioncited by 29
  28. 2018Learning Single-Image Depth from Videos using Quality Assessment Networkscited by 25
  29. 2021Depth Completion using Plane-Residual Representationcited by 24
  30. 2020Boosting Monocular Depth Estimation with Lightweight 3D Point Fusioncited by 14
  31. 2022Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depthcited by 11

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 2.

6 papers.

  1. 2024Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimationcited by 74
  2. 2024OMNI-DC: Highly Robust Depth Completion with Multiresolution Depth Integrationcited by 30
  3. 2024Depth Prompting for Sensor-Agnostic Depth Estimationcited by 26
  4. 2025Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimationcited by 21
  5. 2023Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedbackcited by 10
  6. 2025PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistencycited by 4