# Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environments

arXiv: https://arxiv.org/abs/1711.06623 · HTML: https://mlsanity.com/paper/1711.06623/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2017.

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

- [Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions](https://mlsanity.com/paper/2208.01166/) (2022)
- [Learning to Detect Mobile Objects from LiDAR Scans Without Labels](https://mlsanity.com/paper/2203.15882/) (2022)
- [BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking](https://mlsanity.com/paper/2205.02301/) (2022)
- [Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception](https://mlsanity.com/paper/2203.11405/) (2022)
- [LiMoSeg: Real-time Bird's Eye View based LiDAR Motion Segmentation](https://mlsanity.com/paper/2111.04875/) (2021)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery](https://mlsanity.com/paper/2310.19080/) (2023)
- [Unsupervised Adaptation from Repeated Traversals for Autonomous Driving](https://mlsanity.com/paper/2303.15286/) (2023)
- [Memorize What Matters: Emergent Scene Decomposition from Multitraverse](https://mlsanity.com/paper/2405.17187/) (2024)
- [DiffuBox: Refining 3D Object Detection with Point Diffusion](https://mlsanity.com/paper/2405.16034/) (2024)
- [Track, Check, Repeat: An EM Approach to Unsupervised Tracking](https://mlsanity.com/paper/2104.03424/) (2021)
- [Spatial Retrieval Augmented Autonomous Driving](https://mlsanity.com/paper/2512.06865/) (2025)
- [Better Monocular 3D Detectors with LiDAR from the Past](https://mlsanity.com/paper/2404.05139/) (2024)
- [Vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection](https://mlsanity.com/paper/2408.03790/) (2024)
- [Improving Robot Localisation by Ignoring Visual Distraction](https://mlsanity.com/paper/2107.11857/) (2021)
- [Visual-Inertial Multi-Instance Dynamic SLAM with Object-level Relocalisation](https://mlsanity.com/paper/2208.04274/) (2022)
- [Self-Improving SLAM in Dynamic Environments: Learning When to Mask](https://mlsanity.com/paper/2210.08350/) (2022)
- [A high-precision self-supervised monocular visual odometry in foggy weather based on robust cycled generative adversarial networks and multi-task learning aided depth estimation](https://mlsanity.com/paper/2203.04812/) (2022)
- [Semantics-Guided Moving Object Segmentation with 3D LiDAR](https://mlsanity.com/paper/2205.03186/) (2022)
- [DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions](https://mlsanity.com/paper/2306.17536/) (2023)
- [RaSCL: Radar to Satellite Crossview Localization](https://mlsanity.com/paper/2504.15899/) (2025)
- [Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features](https://mlsanity.com/paper/2309.12140/) (2023)

## Abstract (arXiv)

We present a self-supervised approach to ignoring "distractors" in camera images for the purposes of robustly estimating vehicle motion in cluttered urban environments. We leverage offline multi-session mapping approaches to automatically generate a per-pixel ephemerality mask and depth map for each input image, which we use to train a deep convolutional network. At run-time we use the predicted ephemerality and depth as an input to a monocular visual odometry (VO) pipeline, using either sparse features or dense photometric matching. Our approach yields metric-scale VO using only a single camera and can recover the correct egomotion even when 90% of the image is obscured by dynamic, independently moving objects. We evaluate our robust VO methods on more than 400km of driving from the Oxford RobotCar Dataset and demonstrate reduced odometry drift and significantly improved egomotion estimation in the presence of large moving vehicles in urban traffic.