# AutoRemover: Automatic Object Removal for Autonomous Driving Videos

arXiv: https://arxiv.org/abs/1911.12588 · HTML: https://mlsanity.com/paper/1911.12588/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2019.

## Built on by (most cited first, 8 of 8)

- [One-Shot Video Inpainting](https://mlsanity.com/paper/2302.14362/) (2023)
- [Robust 2D/3D Vehicle Parsing in CVIS](https://mlsanity.com/paper/2103.06432/) (2021)
- [Inpainting-Driven Mask Optimization for Object Removal](https://mlsanity.com/paper/2403.15849/) (2024)
- [From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting](https://mlsanity.com/paper/2607.14976/) (2026)
- [What Do They See? Interpreting Complex Road Scenarios Through the Eyes of Vision-Language-Action Models for Safe and Trustworthy Autonomous Vehicle Learning](https://mlsanity.com/paper/2607.16938/) (2026)
- [Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques](https://mlsanity.com/paper/2401.17883/) (2024)
- [Multi-scale Semantic Prior Features Guided Deep Neural Network for Urban Street-view Image](https://mlsanity.com/paper/2405.10504/) (2024)
- [Revisiting Shadow Detection from a Vision-Language Perspective](https://mlsanity.com/paper/2605.11771/) (2026)

## Abstract (arXiv)

Motivated by the need for photo-realistic simulation in autonomous driving, in this paper we present a video inpainting algorithm AutoRemover, designed specifically for generating street-view videos without any moving objects. In our setup we have two challenges: the first is the shadow, shadows are usually unlabeled but tightly coupled with the moving objects. The second is the large ego-motion in the videos. To deal with shadows, we build up an autonomous driving shadow dataset and design a deep neural network to detect shadows automatically. To deal with large ego-motion, we take advantage of the multi-source data, in particular the 3D data, in autonomous driving. More specifically, the geometric relationship between frames is incorporated into an inpainting deep neural network to produce high-quality structurally consistent video output. Experiments show that our method outperforms other state-of-the-art (SOTA) object removal algorithms, reducing the RMSE by over 19%.