# Crowd Source Scene Change Detection and Local Map Update

arXiv: https://arxiv.org/abs/2203.05205 · HTML: https://mlsanity.com/paper/2203.05205/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 40 references that are in the map.
- First posted on arXiv 10 Mar 2022.

## Builds on (most cited first, 14 of 14)

- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [ResNeSt: Split-Attention Networks](https://mlsanity.com/paper/2004.08955/) (2020)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [RPM-Net: Robust Point Matching using Learned Features](https://mlsanity.com/paper/2003.13479/) (2020)
- [RANSAC-Flow: generic two-stage image alignment](https://mlsanity.com/paper/2004.01526/) (2020)
- [Weakly Supervised Silhouette-based Semantic Scene Change Detection](https://mlsanity.com/paper/1811.11985/) (2018)
- [Learning to Measure Change: Fully Convolutional Siamese Metric Networks for Scene Change Detection](https://mlsanity.com/paper/1810.09111/) (2018)
- [DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds](https://mlsanity.com/paper/1811.11397/) (2018)
- [Visual Localization Using Sparse Semantic 3D Map](https://mlsanity.com/paper/1904.03803/) (2019)
- [City-scale Scene Change Detection using Point Clouds](https://mlsanity.com/paper/2103.14314/) (2021)

## Abstract (arXiv)

As scene changes with time map descriptors become outdated, affecting VPS localization accuracy. In this work, we propose an approach to detect structural and texture scene changes to be followed by map update. In our method - map includes 3D points with descriptors generated either via LiDAR or SFM. Common approaches suffer from shortcomings: 1) Direct comparison of the two point-clouds for change detection is slow due to the need to build new point-cloud every time we want to compare; 2) Image based comparison requires to keep the map images adding substantial storage overhead. To circumvent this problems, we propose an approach based on point-clouds descriptors comparison: 1) Based on VPS poses select close query and map images pairs, 2) Registration of query images to map image descriptors, 3) Use segmentation to filter out dynamic or short term temporal changes, 4) Compare the descriptors between corresponding segments.