# DF-VO: What Should Be Learnt for Visual Odometry?

arXiv: https://arxiv.org/abs/2103.00933 · HTML: https://mlsanity.com/paper/2103.00933/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 69 references that are in the map.
- First posted on arXiv 1 Mar 2021.

## Builds on (most cited first, 30 of 40)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video](https://mlsanity.com/paper/1908.10553/) (2019)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [DeMoN: Depth and Motion Network for Learning Monocular Stereo](https://mlsanity.com/paper/1612.02401/) (2016)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields](https://mlsanity.com/paper/1502.07411/) (2015)
- [Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction](https://mlsanity.com/paper/1803.03893/) (2018)
- [CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction](https://mlsanity.com/paper/1704.03489/) (2017)
- [Deep Convolutional Neural Fields for Depth Estimation from a Single Image](https://mlsanity.com/paper/1411.6387/) (2014)
- [Learning to See by Moving](https://mlsanity.com/paper/1505.01596/) (2015)
- [UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning](https://mlsanity.com/paper/1709.06841/) (2017)
- [DeepTAM: Deep Tracking and Mapping](https://mlsanity.com/paper/1808.01900/) (2018)
- [Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry](https://mlsanity.com/paper/1807.02570/) (2018)

## Built on by (most cited first, 22 of 22)

- [VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences](https://mlsanity.com/paper/2507.16443/) (2025)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment](https://mlsanity.com/paper/2403.18274/) (2024)
- [GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats](https://mlsanity.com/paper/2503.08071/) (2025)
- [D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance](https://mlsanity.com/paper/2207.08794/) (2022)
- [Transformer-Based Model for Monocular Visual Odometry: A Video Understanding Approach](https://mlsanity.com/paper/2305.06121/) (2023)
- [Dense Prediction Transformer for Scale Estimation in Monocular Visual Odometry](https://mlsanity.com/paper/2210.01723/) (2022)
- [ZeroVO: Visual Odometry with Minimal Assumptions](https://mlsanity.com/paper/2506.08005/) (2025)
- [SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenes](https://mlsanity.com/paper/2511.18290/) (2025)
- [Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry](https://mlsanity.com/paper/2412.16923/) (2024)
- [DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion](https://mlsanity.com/paper/2509.06023/) (2025)
- [S-MUSt3R: Sliding Multi-view 3D Reconstruction](https://mlsanity.com/paper/2602.04517/) (2026)
- [RAUM-VO: Rotational Adjusted Unsupervised Monocular Visual Odometry](https://mlsanity.com/paper/2203.07162/) (2022)
- [UNO: Unified Self-Supervised Monocular Odometry for Platform-Agnostic Deployment](https://mlsanity.com/paper/2506.07013/) (2025)
- [Dark3R: Learning Structure from Motion in the Dark](https://mlsanity.com/paper/2603.05330/) (2026)
- [An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open World](https://mlsanity.com/paper/2504.11698/) (2025)
- [FusionDepth: Complement Self-Supervised Monocular Depth Estimation with Cost Volume](https://mlsanity.com/paper/2305.06036/) (2023)
- [Robust Vehicle Localization and Tracking in Rain using Street Maps](https://mlsanity.com/paper/2409.01038/) (2024)
- [VOCAL: Visual Odometry via ContrAstive Learning](https://mlsanity.com/paper/2507.00243/) (2025)
- [Dense-depth map guided deep Lidar-Visual Odometry with Sparse Point Clouds and Images](https://mlsanity.com/paper/2507.15496/) (2025)
- [MDE-VIO: Enhancing Visual-Inertial Odometry Using Learned Depth Priors](https://mlsanity.com/paper/2602.11323/) (2026)
- [Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes](https://mlsanity.com/paper/2606.30436/) (2026)

## Abstract (arXiv)

Multi-view geometry-based methods dominate the last few decades in monocular Visual Odometry for their superior performance, while they have been vulnerable to dynamic and low-texture scenes. More importantly, monocular methods suffer from scale-drift issue, i.e., errors accumulate over time. Recent studies show that deep neural networks can learn scene depths and relative camera in a self-supervised manner without acquiring ground truth labels. More surprisingly, they show that the well-trained networks enable scale-consistent predictions over long videos, while the accuracy is still inferior to traditional methods because of ignoring geometric information. Building on top of recent progress in computer vision, we design a simple yet robust VO system by integrating multi-view geometry and deep learning on Depth and optical Flow, namely DF-VO. In this work, a) we propose a method to carefully sample high-quality correspondences from deep flows and recover accurate camera poses with a geometric module; b) we address the scale-drift issue by aligning geometrically triangulated depths to the scale-consistent deep depths, where the dynamic scenes are taken into account. Comprehensive ablation studies show the effectiveness of the proposed method, and extensive evaluation results show the state-of-the-art performance of our system, e.g., Ours (1.652%) v.s. ORB-SLAM (3.247%) in terms of translation error in KITTI Odometry benchmark. Source code is publicly available at: hrefhttps://github.com/Huangying-Zhan/DF-VODF-VO.