mlsanityData to 7 Oct 2026

Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation

arXiv 1808.00769 ↗First posted 2 Aug 2018cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth completion and semantic segmentation changing only the last layer. Our proposal efficiently learns sparse features without the need of an additional validity mask. We show how to ensure network robustness to varying input sparsities. Our method even works with densities as low as 0.8% (8 layer lidar), and outperforms all published state-of-the-art on the Kitti depth completion benchmark.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 17; 2023: 16; 2024: 13; 2025: 6; 2026: 3.

76 papers.

Sort:

By area:

  1. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  2. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  3. 2021RigNet: Repetitive Image Guided Network for Depth Completioncited by 80
  4. 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
  5. 2021Radar-Camera Pixel Depth Association for Depth Completioncited by 49
  6. 2024Tri-Perspective View Decomposition for Geometry-Aware Depth Completioncited by 42
  7. 2021Depth Completion with Twin Surface Extrapolation at Occlusion Boundariescited by 41
  8. 2021Learning Topology from Synthetic Data for Unsupervised Depth Completioncited by 38
  9. 2022Deep Depth Completion from Extremely Sparse Data: A Surveycited by 33
  10. 2021Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression Networkcited by 32
  11. 2021An Adaptive Framework for Learning Unsupervised Depth Completioncited by 30
  12. 2022Sensing Theorems for Unsupervised Learning in Linear Inverse Problemscited by 28
38 more
  1. 2021BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learningcited by 26
  2. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  3. 2024Test-Time Adaptation for Depth Completioncited by 26
  4. 2022Monitored Distillation for Positive Congruent Depth Completioncited by 24
  5. 2022Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completioncited by 23
  6. 2022GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNscited by 23
  7. 2021MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understandingcited by 22
  8. 2023EVEN: An Event-Based Framework for Monocular Depth Estimation at Adverse Night Conditionscited by 19
  9. 2021A Surface Geometry Model for LiDAR Depth Completioncited by 18
  10. 2023AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimationcited by 15
  11. 2022Depth Completion using Geometry-Aware Embeddingcited by 12
  12. 2023FDCT: Fast Depth Completion for Transparent Objectscited by 12
  13. 2024Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completioncited by 12
  14. 2023RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completioncited by 11
  15. 2023Decomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completioncited by 10
  16. 2023Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedbackcited by 10
  17. 2024Pixel to Elevation: Learning to Predict Elevation Maps at Long Range using Images for Autonomous Offroad Navigationcited by 10
  18. 2025LiDPM: Rethinking Point Diffusion for Lidar Scene Completioncited by 10
  19. 2023AGG-Net: Attention Guided Gated-convolutional Network for Depth Image Completioncited by 8
  20. 2023Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater Robotscited by 8
  21. 2024RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methodscited by 8
  22. 2024Cross-spectral Gated-RGB Stereo Depth Estimationcited by 8
  23. 2021LiDARTouch: Monocular metric depth estimation with a few-beam LiDARcited by 7
  24. 2023Gated Stereo: Joint Depth Estimation from Gated and Wide-Baseline Active Stereo Cuescited by 7
  25. 2024GET-UP: GEomeTric-aware Depth Estimation with Radar Points UPsamplingcited by 7
  26. 2021Gated2Gated: Self-Supervised Depth Estimation from Gated Imagescited by 6
  27. 2022A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Mapscited by 6
  28. 2022Learning an Efficient Multimodal Depth Completion Modelcited by 6
  29. 2022CU-Net: LiDAR Depth-Only Completion With Coupled U-Netcited by 6
  30. 2021PDC: Piecewise Depth Completion utilizing Superpixelscited by 5
  31. 2023Learning to Estimate Two Dense Depths from LiDAR and Event Datacited by 5
  32. 2025Radar-Guided Polynomial Fitting for Metric Depth Estimationcited by 5
  33. 2022Depth Estimation by Combining Binocular Stereo and Monocular Structured-Lightcited by 4
  34. 2022Dense Depth Distillation with Out-of-Distribution Simulated Imagescited by 4
  35. 2023Revisiting Deformable Convolution for Depth Completioncited by 4
  36. 2025ETA: Energy-based Test-time Adaptation for Depth Completioncited by 4
  37. 2021DVMN: Dense Validity Mask Network for Depth Completioncited by 3
  38. 2022Center Feature Fusion: Selective Multi-Sensor Fusion of Center-based Objectscited by 3

50 most cited of 76 All 76 (JSON)