# RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes

arXiv: https://arxiv.org/abs/2004.06267 · HTML: https://mlsanity.com/paper/2004.06267/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2020.

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

- [Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image](https://mlsanity.com/paper/2406.04343/) (2024)
- [Self-Supervised Pretraining for RGB-D Salient Object Detection](https://mlsanity.com/paper/2101.12482/) (2021)
- [Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentation](https://mlsanity.com/paper/2108.05076/) (2021)
- [Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction](https://mlsanity.com/paper/2203.04895/) (2022)
- [Adaptive Multi-source Predictor for Zero-shot Video Object Segmentation](https://mlsanity.com/paper/2303.10383/) (2023)
- [Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction](https://mlsanity.com/paper/2504.13419/) (2025)

## Abstract (arXiv)

We present a generalised self-supervised learning approach for monocular estimation of the real depth across scenes with diverse depth ranges from 1--100s of meters. Existing supervised methods for monocular depth estimation require accurate depth measurements for training. This limitation has led to the introduction of self-supervised methods that are trained on stereo image pairs with a fixed camera baseline to estimate disparity which is transformed to depth given known calibration. Self-supervised approaches have demonstrated impressive results but do not generalise to scenes with different depth ranges or camera baselines. In this paper, we introduce RealMonoDepth a self-supervised monocular depth estimation approach which learns to estimate the real scene depth for a diverse range of indoor and outdoor scenes. A novel loss function with respect to the true scene depth based on relative depth scaling and warping is proposed. This allows self-supervised training of a single network with multiple data sets for scenes with diverse depth ranges from both stereo pair and in the wild moving camera data sets. A comprehensive performance evaluation across five benchmark data sets demonstrates that RealMonoDepth provides a single trained network which generalises depth estimation across indoor and outdoor scenes, consistently outperforming previous self-supervised approaches.