# DSLR: Dynamic to Static LiDAR Scan Reconstruction Using Adversarially Trained Autoencoder

arXiv: https://arxiv.org/abs/2105.12774 · HTML: https://mlsanity.com/paper/2105.12774/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 26 May 2021.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes](https://mlsanity.com/paper/1806.05620/) (2018)
- [SuMa++: Efficient LiDAR-based Semantic SLAM](https://mlsanity.com/paper/2105.11320/) (2021)
- [Deep Generative Modeling of LiDAR Data](https://mlsanity.com/paper/1812.01180/) (2018)
- [Unpaired Point Cloud Completion on Real Scans using Adversarial Training](https://mlsanity.com/paper/1904.00069/) (2019)
- [Multimodal Shape Completion via Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2003.07717/) (2020)
- [LO-Net: Deep Real-time Lidar Odometry](https://mlsanity.com/paper/1904.08242/) (2019)
- [Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images](https://mlsanity.com/paper/1508.04546/) (2015)
- [Learning Representations and Generative Models for 3D Point Clouds](https://mlsanity.com/paper/1707.02392/) (2017)
- [Dynamic Object Removal and Spatio-Temporal RGB-D Inpainting via Geometry-Aware Adversarial Learning](https://mlsanity.com/paper/2008.05058/) (2020)
- [Empty Cities: Image Inpainting for a Dynamic-Object-Invariant Space](https://mlsanity.com/paper/1809.10239/) (2018)
- [Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds](https://mlsanity.com/paper/1910.03336/) (2019)

## Built on by (most cited first, 3 of 3)

- [GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Clouds](https://mlsanity.com/paper/2312.00068/) (2023)
- [MOVES: Movable and Moving LiDAR Scene Segmentation in Label-Free settings using Static Reconstruction](https://mlsanity.com/paper/2306.14812/) (2023)
- [SLACK: Attacking LiDAR-based SLAM with Adversarial Point Injections](https://mlsanity.com/paper/2504.03089/) (2025)

## Abstract (arXiv)

Accurate reconstruction of static environments from LiDAR scans of scenes containing dynamic objects, which we refer to as Dynamic to Static Translation (DST), is an important area of research in Autonomous Navigation. This problem has been recently explored for visual SLAM, but to the best of our knowledge no work has been attempted to address DST for LiDAR scans. The problem is of critical importance due to wide-spread adoption of LiDAR in Autonomous Vehicles. We show that state-of the art methods developed for the visual domain when adapted for LiDAR scans perform poorly. We develop DSLR, a deep generative model which learns a mapping between dynamic scan to its static counterpart through an adversarially trained autoencoder. Our model yields the first solution for DST on LiDAR that generates static scans without using explicit segmentation labels. DSLR cannot always be applied to real world data due to lack of paired dynamic-static scans. Using Unsupervised Domain Adaptation, we propose DSLR-UDA for transfer to real world data and experimentally show that this performs well in real world settings. Additionally, if segmentation information is available, we extend DSLR to DSLR-Seg to further improve the reconstruction quality. DSLR gives the state of the art performance on simulated and real-world datasets and also shows at least 4x improvement. We show that DSLR, unlike the existing baselines, is a practically viable model with its reconstruction quality within the tolerable limits for tasks pertaining to autonomous navigation like SLAM in dynamic environments.