mlsanityData to 7 Oct 2026

SparseDC: Depth Completion from sparse and non-uniform inputs

arXiv 2312.00097 ↗First posted 30 Nov 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

We propose SparseDC, a model for Depth Completion of Sparse and non-uniform depth inputs. Unlike previous methods focusing on completing fixed distributions on benchmark datasets (e.g., NYU with 500 points, KITTI with 64 lines), SparseDC is specifically designed to handle depth maps with poor quality in real usage. The key contributions of SparseDC are two-fold. First, we design a simple strategy, called SFFM, to improve the robustness under sparse input by explicitly filling the unstable depth features with stable image features. Second, we propose a two-branch feature embedder to predict both the precise local geometry of regions with available depth values and accurate structures in regions with no depth. The key of the embedder is an uncertainty-based fusion module called UFFM to balance the local and long-term information extracted by CNNs and ViTs. Extensive indoor and outdoor experiments demonstrate the robustness of our framework when facing sparse and non-uniform input depths. The pre-trained model and code are available at https://github.com/WHU-USI3DV/SparseDC.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 35 of its 57 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

35 of 57 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  6. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  7. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  8. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  9. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 373
  10. 2017Sparsity Invariant CNNscited by 325
  11. 2017Submanifold Sparse Convolutional Networkscited by 223
  12. 2020Non-Local Spatial Propagation Network for Depth Completioncited by 194
23 more
  1. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  2. 2018Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundariescited by 144
  3. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  4. 2019Learning Guided Convolutional Network for Depth Completioncited by 111
  5. 2019CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completioncited by 110
  6. 2018Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Networkcited by 109
  7. 2019Depth Completion from Sparse LiDAR Data with Depth-Normal Constraintscited by 108
  8. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 92
  9. 2017Intel RealSense Stereoscopic Depth Camerascited by 82
  10. 2022Dynamic Spatial Propagation Network for Depth Completioncited by 70
  11. 2020Adaptive Context-Aware Multi-Modal Network for Depth Completioncited by 69
  12. 2023LRRU: Long-short Range Recurrent Updating Networks for Depth Completioncited by 48
  13. 2022Guided Depth Super-Resolution by Deep Anisotropic Diffusioncited by 46
  14. 2020FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completioncited by 45
  15. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  16. 2022Sparsity Agnostic Depth Completioncited by 27
  17. 2022GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNscited by 23
  18. 2021DenseLiDAR: A Real-Time Pseudo Dense Depth Guided Depth Completion Networkcited by 17
  19. 2023URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimationcited by 16
  20. 2021PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimationcited by 12
  21. 2021PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsamplingcited by 11
  22. 2022Sparse SPN: Depth Completion from Sparse Keypointscited by 3
  23. 2022Segmentation-guided Domain Adaptation for Efficient Depth Completioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 4; 2026: 1.

8 papers.

  1. 2024OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterationscited by 23
  2. 2025Multi-view Reconstruction via SfM-guided Monocular Depth Estimationcited by 17
  3. 2024Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completioncited by 9
  4. 2025PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistencycited by 4
  5. 2025SPADE: Sparsity Adaptive Depth Estimator for Zero-Shot, Real-Time, Monocular Depth Estimation in Underwater Environmentscited by 1
  6. 2024WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model Researchcited by 0
  7. 2025Geometry-Aware Sparse Depth Sampling for High-Fidelity RGB-D Depth Completion in Robotic Systemscited by 0
  8. 2026Real-Time LiDAR Point Cloud Densification for Low-Latency Spatial Data Transmissioncited by 0