# Sparse SPN: Depth Completion from Sparse Keypoints

arXiv: https://arxiv.org/abs/2212.00987 · HTML: https://mlsanity.com/paper/2212.00987/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 2 Dec 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Non-Local Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2007.10042/) (2020)
- [Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image](https://mlsanity.com/paper/1709.07492/) (2017)
- [PENet: Towards Precise and Efficient Image Guided Depth Completion](https://mlsanity.com/paper/2103.00783/) (2021)
- [Learning Depth with Convolutional Spatial Propagation Network](https://mlsanity.com/paper/1810.02695/) (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)
- [3D Common Corruptions and Data Augmentation](https://mlsanity.com/paper/2203.01441/) (2022)
- [Deep Depth Completion of a Single RGB-D Image](https://mlsanity.com/paper/1803.09326/) (2018)
- [CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion](https://mlsanity.com/paper/1911.05377/) (2019)
- [Depth Completion from Sparse LiDAR Data with Depth-Normal Constraints](https://mlsanity.com/paper/1910.06727/) (2019)
- [Multi-Scale Geometric Consistency Guided Multi-View Stereo](https://mlsanity.com/paper/1904.08103/) (2019)
- [Unsupervised Depth Completion from Visual Inertial Odometry](https://mlsanity.com/paper/1905.08616/) (2019)
- [Learning Affinity via Spatial Propagation Networks](https://mlsanity.com/paper/1710.01020/) (2017)
- [Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation](https://mlsanity.com/paper/1808.00769/) (2018)
- [Dynamic Spatial Propagation Network for Depth Completion](https://mlsanity.com/paper/2202.09769/) (2022)
- [Adaptive Context-Aware Multi-Modal Network for Depth Completion](https://mlsanity.com/paper/2008.10833/) (2020)
- [Unsupervised Depth Completion with Calibrated Backprojection Layers](https://mlsanity.com/paper/2108.10531/) (2021)
- [Learning Topology from Synthetic Data for Unsupervised Depth Completion](https://mlsanity.com/paper/2106.02994/) (2021)
- [CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth](https://mlsanity.com/paper/2012.10133/) (2020)
- [Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion](https://mlsanity.com/paper/1906.08967/) (2019)
- [Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion](https://mlsanity.com/paper/2012.10296/) (2020)
- [Deep Depth Estimation from Visual-Inertial SLAM](https://mlsanity.com/paper/2008.00092/) (2020)

## Built on by (most cited first, 3 of 3)

- [Multi-view Reconstruction via SfM-guided Monocular Depth Estimation](https://mlsanity.com/paper/2503.14483/) (2025)
- [SparseDC: Depth Completion from sparse and non-uniform inputs](https://mlsanity.com/paper/2312.00097/) (2023)
- [4Director: Controlling Video World Models with Rigid 3D Geometry](https://mlsanity.com/paper/2610.02160/) (2026)

## Abstract (arXiv)

Our long term goal is to use image-based depth completion to quickly create 3D models from sparse point clouds, e.g. from SfM or SLAM. Much progress has been made in depth completion. However, most current works assume well distributed samples of known depth, e.g. Lidar or random uniform sampling, and perform poorly on uneven samples, such as from keypoints, due to the large unsampled regions. To address this problem, we extend CSPN with multiscale prediction and a dilated kernel, leading to much better completion of keypoint-sampled depth. We also show that a model trained on NYUv2 creates surprisingly good point clouds on ETH3D by completing sparse SfM points.