mlsanityData to 7 Oct 2026

PDC: Piecewise Depth Completion utilizing Superpixels

arXiv 2107.06711 ↗First posted 14 Jul 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Depth completion from sparse LiDAR and high-resolution RGB data is one of the foundations for autonomous driving techniques. Current approaches often rely on CNN-based methods with several known drawbacks: flying pixel at depth discontinuities, overfitting to both a given data set as well as error metric, and many more. Thus, we propose our novel Piecewise Depth Completion (PDC), which works completely without deep learning. PDC segments the RGB image into superpixels corresponding the regions with similar depth value. Superpixels corresponding to same objects are gathered using a cost map. At the end, we receive detailed depth images with state of the art accuracy. In our evaluation, we can show both the influence of the individual proposed processing steps and the overall performance of our method on the challenging KITTI dataset.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 14 of its 20 references that are in the map. First posted on arXiv 14 Jul 2021.

Builds on

14 of 20 references.

References · 14

  1. 2017Sparsity Invariant CNNscited by 325
  2. 2018Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Cameracited by 140
  3. 2018DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Imagecited by 129
  4. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  5. 2015EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flowcited by 80
  6. 2018Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentationcited by 76
  7. 2013SEEDS: Superpixels Extracted via Energy-Driven Samplingcited by 75
  8. 2014Fast Edge Detection Using Structured Forestscited by 64
  9. 2019DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completioncited by 38
  10. 2018Propagating Confidences through CNNs for Sparse Data Regressioncited by 36
  11. 2018Deep Convolutional Compressed Sensing for LiDAR Depth Completioncited by 27
  12. 2019LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Imagescited by 12
2 more
  1. 2020SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolationcited by 12
  2. 2019DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidancecited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 3.

5 papers.

  1. 2022Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completioncited by 23
  2. 2023360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentationcited by 12
  3. 2025Region-aware Depth Scale Adaptation with Sparse Measurementscited by 3
  4. 2025DenseFormer: Learning Dense Depth Map from Sparse Depth and Image via Conditional Diffusion Modelcited by 1
  5. 2025Training Self-Supervised Depth Completion Using Sparse Measurements and a Single Imagecited by 0