# Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network

arXiv: https://arxiv.org/abs/1905.07542 · HTML: https://mlsanity.com/paper/1905.07542/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 May 2019.

## Built on by (most cited first, 21 of 21)

- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [UDepth: Fast Monocular Depth Estimation for Visually-guided Underwater Robots](https://mlsanity.com/paper/2209.12358/) (2022)
- [Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching](https://mlsanity.com/paper/2307.16509/) (2023)
- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator](https://mlsanity.com/paper/2502.19204/) (2025)
- [Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation](https://mlsanity.com/paper/2203.09737/) (2022)
- [Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.05315/) (2022)
- [LiDARTouch: Monocular metric depth estimation with a few-beam LiDAR](https://mlsanity.com/paper/2109.03569/) (2021)
- [3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling](https://mlsanity.com/paper/2209.09231/) (2022)
- [Recent Advancements in Deep Learning Applications and Methods for Autonomous Navigation: A Comprehensive Review](https://mlsanity.com/paper/2302.11089/) (2023)
- [Pix2Point: Learning Outdoor 3D Using Sparse Point Clouds and Optimal Transport](https://mlsanity.com/paper/2107.14498/) (2021)
- [UAMD-Net: A Unified Adaptive Multimodal Neural Network for Dense Depth Completion](https://mlsanity.com/paper/2204.07791/) (2022)
- [Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data](https://mlsanity.com/paper/2109.11573/) (2021)
- [ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimation](https://mlsanity.com/paper/2309.14744/) (2023)
- [VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction](https://mlsanity.com/paper/2104.05932/) (2021)
- [Online Mutual Adaptation of Deep Depth Prediction and Visual SLAM](https://mlsanity.com/paper/2111.04096/) (2021)
- [Do More With What You Have: Transferring Depth-Scale from Labeled to Unlabeled Domains](https://mlsanity.com/paper/2303.07662/) (2023)
- [Consistency Regularisation for Unsupervised Domain Adaptation in Monocular Depth Estimation](https://mlsanity.com/paper/2405.17704/) (2024)
- [Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometry](https://mlsanity.com/paper/2406.00929/) (2024)
- [Endoscopic Depth Estimation Based on Deep Learning: A Survey](https://mlsanity.com/paper/2507.20881/) (2025)
- [MaskingDepth: Masked Consistency Regularization for Semi-supervised Monocular Depth Estimation](https://mlsanity.com/paper/2212.10806/) (2022)

## Abstract (arXiv)

There has been tremendous research progress in estimating the depth of a scene from a monocular camera image. Existing methods for single-image depth prediction are exclusively based on deep neural networks, and their training can be unsupervised using stereo image pairs, supervised using LiDAR point clouds, or semi-supervised using both stereo and LiDAR. In general, semi-supervised training is preferred as it does not suffer from the weaknesses of either supervised training, resulting from the difference in the cameras and the LiDARs field of view, or unsupervised training, resulting from the poor depth accuracy that can be recovered from a stereo pair. In this paper, we present our research in single image depth prediction using semi-supervised training that outperforms the state-of-the-art. We achieve this through a loss function that explicitly exploits left-right consistency in a stereo reconstruction, which has not been adopted in previous semi-supervised training. In addition, we describe the correct use of ground truth depth derived from LiDAR that can significantly reduce prediction error. The performance of our depth prediction model is evaluated on popular datasets, and the importance of each aspect of our semi-supervised training approach is demonstrated through experimental results. Our deep neural network model has been made publicly available.