mlsanityData to 7 Oct 2026

S3: Learnable Sparse Signal Superdensity for Guided Depth Estimation

arXiv 2103.02396 ↗First posted 3 Mar 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g., LiDAR and Radar, has been leveraged as guidance for enhancing dense depth estimation, the improvement is limited due to its low density and imbalanced distribution. To maximize the utility from the sparse source, we propose S3 technique, which expands the depth value from sparse cues while estimating the confidence of expanded region. The proposed S3 can be applied to various guided depth estimation approaches and trained end-to-end at different stages, including input, cost volume and output. Extensive experiments demonstrate the effectiveness, robustness, and flexibility of the S3 technique on LiDAR and Radar signal.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

29 of 53 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  6. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  7. 2018Pyramid Stereo Matching Networkcited by 486
  8. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  9. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  10. 2017Sparsity Invariant CNNscited by 325
  11. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
  12. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
17 more
  1. 2017Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Imagecited by 159
  2. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  3. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  4. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  5. 2018Deep Depth Completion of a Single RGB-D Imagecited by 110
  6. 2013SEEDS: Superpixels Extracted via Energy-Driven Samplingcited by 75
  7. 2020Learning Joint 2D-3D Representations for Depth Completioncited by 71
  8. 2020A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detectioncited by 70
  9. 2019Distant Vehicle Detection Using Radar and Visioncited by 44
  10. 2019DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completioncited by 38
  11. 2019Noise-Aware Unsupervised Deep Lidar-Stereo Fusioncited by 31
  12. 2019Indoor Depth Completion with Boundary Consistency and Self-Attentioncited by 29
  13. 2019Guided Stereo Matchingcited by 24
  14. 2019Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completioncited by 20
  15. 20193D LiDAR and Stereo Fusion using Stereo Matching Network with Conditional Cost Volume Normalizationcited by 17
  16. 2018Real Time Dense Depth Estimation by Fusing Stereo with Sparse Depth Measurementscited by 5
  17. 2019300 GHz Radar Object Recognition based on Deep Neural Networks and Transfer Learningcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 3; 2024: 4; 2025: 1.

10 papers.

  1. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  2. 2023Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalizationcited by 18
  3. 2023Active Stereo Without Pattern Projectorcited by 8
  4. 2024LiDAR-Event Stereo Fusion with Hallucinationscited by 6
  5. 2022SST: Real-time End-to-end Monocular 3D Reconstruction via Sparse Spatial-Temporal Guidancecited by 4
  6. 2024Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth Conversioncited by 4
  7. 2022Expansion of Visual Hints for Improved Generalization in Stereo Matchingcited by 3
  8. 2023Depth-Relative Self Attention for Monocular Depth Estimationcited by 1
  9. 2024Active Stereo in the Wild through Virtual Pattern Projectioncited by 0
  10. 2025Preserving Guidance in Cost-Volume Retrieval under Extreme LiDAR Sparsity in Iterative Stereocited by 0