# PDC: Piecewise Depth Completion utilizing Superpixels

arXiv: https://arxiv.org/abs/2107.06711 · HTML: https://mlsanity.com/paper/2107.06711/

## Key facts

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

## Builds on (most cited first, 14 of 14)

- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera](https://mlsanity.com/paper/1807.00275/) (2018)
- [DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image](https://mlsanity.com/paper/1812.00488/) (2018)
- [In Defense of Classical Image Processing: Fast Depth Completion on the CPU](https://mlsanity.com/paper/1802.00036/) (2018)
- [EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow](https://mlsanity.com/paper/1501.02565/) (2015)
- [Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation](https://mlsanity.com/paper/1808.00769/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Fast Edge Detection Using Structured Forests](https://mlsanity.com/paper/1406.5549/) (2014)
- [DFuseNet: Deep Fusion of RGB and Sparse Depth Information for Image Guided Dense Depth Completion](https://mlsanity.com/paper/1902.00761/) (2019)
- [Propagating Confidences through CNNs for Sparse Data Regression](https://mlsanity.com/paper/1805.11913/) (2018)
- [Deep Convolutional Compressed Sensing for LiDAR Depth Completion](https://mlsanity.com/paper/1803.08949/) (2018)
- [LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Images](https://mlsanity.com/paper/1910.14453/) (2019)
- [SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation](https://mlsanity.com/paper/2008.09346/) (2020)
- [DFineNet: Ego-Motion Estimation and Depth Refinement from Sparse, Noisy Depth Input with RGB Guidance](https://mlsanity.com/paper/1903.06397/) (2019)

## Built on by (most cited first, 5 of 5)

- [Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion](https://mlsanity.com/paper/2203.09855/) (2022)
- [360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentation](https://mlsanity.com/paper/2309.06197/) (2023)
- [Region-aware Depth Scale Adaptation with Sparse Measurements](https://mlsanity.com/paper/2507.14879/) (2025)
- [DenseFormer: Learning Dense Depth Map from Sparse Depth and Image via Conditional Diffusion Model](https://mlsanity.com/paper/2503.23993/) (2025)
- [Training Self-Supervised Depth Completion Using Sparse Measurements and a Single Image](https://mlsanity.com/paper/2507.14845/) (2025)

## 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.