# GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose

arXiv: https://arxiv.org/abs/1803.02276 · HTML: https://mlsanity.com/paper/1803.02276/

## Key facts

- Cited by 342 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Mar 2018.

## Built on by (most cited first, 30 of 342)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation](https://mlsanity.com/paper/2404.15506/) (2024)
- [Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image](https://mlsanity.com/paper/2307.10984/) (2023)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Robust Dynamic Radiance Fields](https://mlsanity.com/paper/2301.02239/) (2023)
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://mlsanity.com/paper/2107.14160/) (2021)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs](https://mlsanity.com/paper/2408.13912/) (2024)
- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer](https://mlsanity.com/paper/2208.03543/) (2022)
- [P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior](https://mlsanity.com/paper/2204.02091/) (2022)
- [Progressively Optimized Local Radiance Fields for Robust View Synthesis](https://mlsanity.com/paper/2303.13791/) (2023)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2211.13202/) (2022)
- [ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild](https://mlsanity.com/paper/2207.09137/) (2022)
- [SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation](https://mlsanity.com/paper/2204.03636/) (2022)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [Unsupervised Scale-consistent Depth Learning from Video](https://mlsanity.com/paper/2105.11610/) (2021)
- [Multi-Frame Self-Supervised Depth with Transformers](https://mlsanity.com/paper/2204.07616/) (2022)
- [Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2112.13047/) (2021)
- [Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency](https://mlsanity.com/paper/2102.02629/) (2021)
- [Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark](https://mlsanity.com/paper/2108.03830/) (2021)
- [OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving](https://mlsanity.com/paper/2102.07448/) (2021)
- [Consistent Depth of Moving Objects in Video](https://mlsanity.com/paper/2108.01166/) (2021)

## Abstract (arXiv)

We propose GeoNet, a jointly unsupervised learning framework for monocular depth, optical flow and ego-motion estimation from videos. The three components are coupled by the nature of 3D scene geometry, jointly learned by our framework in an end-to-end manner. Specifically, geometric relationships are extracted over the predictions of individual modules and then combined as an image reconstruction loss, reasoning about static and dynamic scene parts separately. Furthermore, we propose an adaptive geometric consistency loss to increase robustness towards outliers and non-Lambertian regions, which resolves occlusions and texture ambiguities effectively. Experimentation on the KITTI driving dataset reveals that our scheme achieves state-of-the-art results in all of the three tasks, performing better than previously unsupervised methods and comparably with supervised ones.