# A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation

arXiv: https://arxiv.org/abs/1904.10230 · HTML: https://mlsanity.com/paper/1904.10230/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2019.

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

- [Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction](https://mlsanity.com/paper/2103.04216/) (2021)
- [Guided Depth Super-Resolution by Deep Anisotropic Diffusion](https://mlsanity.com/paper/2211.11592/) (2022)
- [Learning Graph Regularisation for Guided Super-Resolution](https://mlsanity.com/paper/2203.14297/) (2022)
- [Guided Depth Map Super-resolution: A Survey](https://mlsanity.com/paper/2302.09598/) (2023)
- [Cross-Modal Knowledge Transfer Without Task-Relevant Source Data](https://mlsanity.com/paper/2209.04027/) (2022)
- [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024)
- [Depth Anything at Any Condition](https://mlsanity.com/paper/2507.01634/) (2025)
- [A Survey on RGB-D Datasets](https://mlsanity.com/paper/2201.05761/) (2022)
- [Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth](https://mlsanity.com/paper/2202.01470/) (2022)
- [RGB Guided ToF Imaging System: A Survey of Deep Learning-based Methods](https://mlsanity.com/paper/2405.10357/) (2024)
- [PHISWID: Physics-Inspired Underwater Image Dataset Synthesized from RGB-D Images](https://mlsanity.com/paper/2404.03998/) (2024)
- [Towards Open-World Generation of Stereo Images and Unsupervised Matching](https://mlsanity.com/paper/2503.12720/) (2025)
- [Automated Distance Estimation for Wildlife Camera Trapping](https://mlsanity.com/paper/2202.04613/) (2022)
- [Depth Super-Resolution from Explicit and Implicit High-Frequency Features](https://mlsanity.com/paper/2303.09307/) (2023)
- [Outdoor Monocular Depth Estimation: A Research Review](https://mlsanity.com/paper/2205.01399/) (2022)
- [Source-Free Cross-Modal Knowledge Transfer by Unleashing the Potential of Task-Irrelevant Data](https://mlsanity.com/paper/2401.05014/) (2024)
- [ORC: Network Group-based Knowledge Distillation using Online Role Change](https://mlsanity.com/paper/2206.01186/) (2022)
- [Do More With What You Have: Transferring Depth-Scale from Labeled to Unlabeled Domains](https://mlsanity.com/paper/2303.07662/) (2023)
- [Multi-Order Matching Network for Alignment-Free Depth Super-Resolution](https://mlsanity.com/paper/2511.16361/) (2025)
- [Minimizing the Effect of Noise and Limited Dataset Size in Image Classification Using Depth Estimation as an Auxiliary Task with Deep Multitask Learning](https://mlsanity.com/paper/2208.10390/) (2022)
- [FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolution](https://mlsanity.com/paper/2609.32323/) (2026)

## Abstract (arXiv)

Current self-supervised methods for monocular depth estimation are largely based on deeply nested convolutional networks that leverage stereo image pairs or monocular sequences during a training phase. However, they often exhibit inaccurate results around occluded regions and depth boundaries. In this paper, we present a simple yet effective approach for monocular depth estimation using stereo image pairs. The study aims to propose a student-teacher strategy in which a shallow student network is trained with the auxiliary information obtained from a deeper and more accurate teacher network. Specifically, we first train the stereo teacher network by fully utilizing the binocular perception of 3-D geometry and then use the depth predictions of the teacher network to train the student network for monocular depth inference. This enables us to exploit all available depth data from massive unlabeled stereo pairs. We propose a strategy that involves the use of a data ensemble to merge the multiple depth predictions of the teacher network to improve the training samples by collecting non-trivial knowledge beyond a single prediction. To refine the inaccurate depth estimation that is used when training the student network, we further propose stereo confidence-guided regression loss that handles the unreliable pseudo depth values in occlusion, texture-less region, and repetitive pattern. To complement the existing dataset comprising outdoor driving scenes, we built a novel large-scale dataset consisting of one million outdoor stereo images taken using hand-held stereo cameras. Finally, we demonstrate that the monocular depth estimation network provides feature representations that are suitable for high-level vision tasks. The experimental results for various outdoor scenarios demonstrate the effectiveness and flexibility of our approach, which outperforms state-of-the-art approaches.