# Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints

arXiv: https://arxiv.org/abs/1802.05522 · HTML: https://mlsanity.com/paper/1802.05522/

## Key facts

- Cited by 179 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2018.

## Built on by (most cited first, 30 of 179)

- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer](https://mlsanity.com/paper/2208.03543/) (2022)
- [MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis](https://mlsanity.com/paper/2103.14910/) (2021)
- [P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior](https://mlsanity.com/paper/2204.02091/) (2022)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation](https://mlsanity.com/paper/2204.03636/) (2022)
- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [Unsupervised Scale-consistent Depth Learning from Video](https://mlsanity.com/paper/2105.11610/) (2021)
- [Can Language Understand Depth?](https://mlsanity.com/paper/2207.01077/) (2022)
- [Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2112.13047/) (2021)
- [360MonoDepth: High-Resolution 360deg Monocular Depth Estimation](https://mlsanity.com/paper/2111.15669/) (2021)
- [Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency](https://mlsanity.com/paper/2102.02629/) (2021)
- [SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes](https://mlsanity.com/paper/2211.03660/) (2022)
- [Scalable Scene Flow from Point Clouds in the Real World](https://mlsanity.com/paper/2103.01306/) (2021)
- [Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth](https://mlsanity.com/paper/2203.15174/) (2022)
- [Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail](https://mlsanity.com/paper/2412.04472/) (2024)
- [Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry](https://mlsanity.com/paper/2112.08177/) (2021)
- [UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering](https://mlsanity.com/paper/2102.11870/) (2021)
- [Full Surround Monodepth from Multiple Cameras](https://mlsanity.com/paper/2104.00152/) (2021)
- [OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments](https://mlsanity.com/paper/2312.09243/) (2023)
- [Deep Two-View Structure-from-Motion Revisited](https://mlsanity.com/paper/2104.00556/) (2021)
- [STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation](https://mlsanity.com/paper/2302.01334/) (2023)
- [RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2207.11984/) (2022)
- [Learning Depth Estimation for Transparent and Mirror Surfaces](https://mlsanity.com/paper/2307.15052/) (2023)
- [SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images](https://mlsanity.com/paper/2101.07422/) (2021)
- [Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation](https://mlsanity.com/paper/2104.05374/) (2021)
- [An Adaptive Framework for Learning Unsupervised Depth Completion](https://mlsanity.com/paper/2106.03010/) (2021)
- [Less is More: Consistent Video Depth Estimation with Masked Frames Modeling](https://mlsanity.com/paper/2208.00380/) (2022)
- [Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions](https://mlsanity.com/paper/2407.16698/) (2024)
- [VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction](https://mlsanity.com/paper/2511.19971/) (2025)

## Abstract (arXiv)

We present a novel approach for unsupervised learning of depth and ego-motion from monocular video. Unsupervised learning removes the need for separate supervisory signals (depth or ego-motion ground truth, or multi-view video). Prior work in unsupervised depth learning uses pixel-wise or gradient-based losses, which only consider pixels in small local neighborhoods. Our main contribution is to explicitly consider the inferred 3D geometry of the scene, enforcing consistency of the estimated 3D point clouds and ego-motion across consecutive frames. This is a challenging task and is solved by a novel (approximate) backpropagation algorithm for aligning 3D structures. We combine this novel 3D-based loss with 2D losses based on photometric quality of frame reconstructions using estimated depth and ego-motion from adjacent frames. We also incorporate validity masks to avoid penalizing areas in which no useful information exists. We test our algorithm on the KITTI dataset and on a video dataset captured on an uncalibrated mobile phone camera. Our proposed approach consistently improves depth estimates on both datasets, and outperforms the state-of-the-art for both depth and ego-motion. Because we only require a simple video, learning depth and ego-motion on large and varied datasets becomes possible. We demonstrate this by training on the low quality uncalibrated video dataset and evaluating on KITTI, ranking among top performing prior methods which are trained on KITTI itself.