# SGTBN: Generating Dense Depth Maps from Single-Line LiDAR

arXiv: https://arxiv.org/abs/2106.12994 · HTML: https://mlsanity.com/paper/2106.12994/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 24 Jun 2021.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [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)
- [CARAFE: Content-Aware ReAssembly of FEatures](https://mlsanity.com/paper/1905.02188/) (2019)
- [Gradient Centralization: A New Optimization Technique for Deep Neural Networks](https://mlsanity.com/paper/2004.01461/) (2020)
- [Sparse and noisy LiDAR completion with RGB guidance and uncertainty](https://mlsanity.com/paper/1902.05356/) (2019)
- [Confidence Propagation through CNNs for Guided Sparse Depth Regression](https://mlsanity.com/paper/1811.01791/) (2018)

## Built on by (most cited first, 6 of 6)

- [Deep Depth Completion from Extremely Sparse Data: A Survey](https://mlsanity.com/paper/2205.05335/) (2022)
- [Predictive World Models from Real-World Partial Observations](https://mlsanity.com/paper/2301.04783/) (2023)
- [Prior based Sampling for Adaptive LiDAR](https://mlsanity.com/paper/2304.07099/) (2023)
- [Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery](https://mlsanity.com/paper/2512.07276/) (2025)
- [Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks](https://mlsanity.com/paper/2605.08320/) (2026)
- [Robust and accurate depth estimation by fusing LiDAR and Stereo](https://mlsanity.com/paper/2207.06139/) (2022)

## Abstract (arXiv)

Depth completion aims to generate a dense depth map from the sparse depth map and aligned RGB image. However, current depth completion methods use extremely expensive 64-line LiDAR(about 100,000) to obtain sparse depth maps, which will limit their application scenarios. Compared with the 64-line LiDAR, the single-line LiDAR is much less expensive and much more robust. Therefore, we propose a method to tackle the problem of single-line depth completion, in which we aim to generate a dense depth map from the single-line LiDAR info and the aligned RGB image. A single-line depth completion dataset is proposed based on the existing 64-line depth completion dataset(KITTI). A network called Semantic Guided Two-Branch Network(SGTBN) which contains global and local branches to extract and fuse global and local info is proposed for this task. A Semantic guided depth upsampling module is used in our network to make full use of the semantic info in RGB images. Except for the usual MSE loss, we add the virtual normal loss to increase the constraint of high-order 3D geometry in our network. Our network outperforms the state-of-the-art in the single-line depth completion task. Besides, compared with the monocular depth estimation, our method also has significant advantages in precision and model size.