# Camera Height Doesn't Change: Unsupervised Training for Metric Monocular Road-Scene Depth Estimation

arXiv: https://arxiv.org/abs/2312.04530 · HTML: https://mlsanity.com/paper/2312.04530/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 63 references that are in the map.
- First posted on arXiv 7 Dec 2023.

## Builds on (most cited first, 30 of 51)

- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image](https://mlsanity.com/paper/2307.10984/) (2023)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [End-to-end Interpretable Neural Motion Planner](https://mlsanity.com/paper/2101.06679/) (2021)
- [One Thousand and One Hours: Self-driving Motion Prediction Dataset](https://mlsanity.com/paper/2006.14480/) (2020)
- [A2D2: Audi Autonomous Driving Dataset](https://mlsanity.com/paper/2004.06320/) (2020)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/1906.06310/) (2019)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [Learning Depth from Monocular Videos using Direct Methods](https://mlsanity.com/paper/1712.00175/) (2017)
- [Perceive, Predict, and Plan: Safe Motion Planning Through Interpretable Semantic Representations](https://mlsanity.com/paper/2008.05930/) (2020)
- [NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation](https://mlsanity.com/paper/2203.01502/) (2022)
- [Train in Germany, Test in The USA: Making 3D Object Detectors Generalize](https://mlsanity.com/paper/2005.08139/) (2020)
- [HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2012.07356/) (2020)

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

- [MonoPP: Metric-Scaled Self-Supervised Monocular Depth Estimation by Planar-Parallax Geometry in Automotive Applications](https://mlsanity.com/paper/2411.19717/) (2024)
- [Gamma-from-Mono: Road-Relative, Metric, Self-Supervised Monocular Geometry for Vehicular Applications](https://mlsanity.com/paper/2512.04303/) (2025)
- [SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2605.28477/) (2026)

## Abstract (arXiv)

In this paper, we introduce a novel training method for making any monocular depth network learn absolute scale and estimate metric road-scene depth just from regular training data, i.e., driving videos. We refer to this training framework as FUMET. The key idea is to leverage cars found on the road as sources of scale supervision and to incorporate them in network training robustly. FUMET detects and estimates the sizes of cars in a frame and aggregates scale information extracted from them into an estimate of the camera height whose consistency across the entire video sequence is enforced as scale supervision. This realizes robust unsupervised training of any, otherwise scale-oblivious, monocular depth network so that they become not only scale-aware but also metric-accurate without the need for auxiliary sensors and extra supervision. Extensive experiments on the KITTI and the Cityscapes datasets show the effectiveness of FUMET, which achieves state-of-the-art accuracy. We also show that FUMET enables training on mixed datasets of different camera heights, which leads to larger-scale training and better generalization. Metric depth reconstruction is essential in any road-scene visual modeling, and FUMET democratizes its deployment by establishing the means to convert any model into a metric depth estimator.