# Objects Can Move: 3D Change Detection by Geometric Transformation Constistency

arXiv: https://arxiv.org/abs/2208.09870 · HTML: https://mlsanity.com/paper/2208.09870/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 41 references that are in the map.
- First posted on arXiv 21 Aug 2022.

## Builds on (most cited first, 11 of 11)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://mlsanity.com/paper/2103.05465/) (2021)
- [MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects](https://mlsanity.com/paper/1804.09194/) (2018)
- [A Generalization of Otsu's Method and Minimum Error Thresholding](https://mlsanity.com/paper/2007.07350/) (2020)
- [Rescan: Inductive Instance Segmentation for Indoor RGBD Scans](https://mlsanity.com/paper/1909.11268/) (2019)
- [Efficient 2D and 3D Facade Segmentation using Auto-Context](https://mlsanity.com/paper/1606.06437/) (2016)

## Built on by (most cited first, 13 of 13)

- [Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments](https://mlsanity.com/paper/2312.09138/) (2023)
- [Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery](https://mlsanity.com/paper/2310.19080/) (2023)
- [A Guide to Structureless Visual Localization](https://mlsanity.com/paper/2504.17636/) (2025)
- [Learn to Memorize and to Forget: A Continual Learning Perspective of Dynamic SLAM](https://mlsanity.com/paper/2407.13338/) (2024)
- [Has Anything Changed? 3D Change Detection by 2D Segmentation Masks](https://mlsanity.com/paper/2312.01148/) (2023)
- [3D Scene Change Modeling With Consistent Multi-View Aggregation](https://mlsanity.com/paper/2512.22830/) (2025)
- [BYE: Build Your Encoder with One Sequence of Exploration Data for Long-Term Dynamic Scene Understanding](https://mlsanity.com/paper/2412.02449/) (2024)
- [Is there anything left? Measuring semantic residuals of objects removed from 3D Gaussian Splatting](https://mlsanity.com/paper/2503.17574/) (2025)
- [Remove360: Benchmarking Residuals After Object Removal in 3D Gaussian Splatting](https://mlsanity.com/paper/2508.11431/) (2025)
- [Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model](https://mlsanity.com/paper/2510.11509/) (2025)
- [ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes](https://mlsanity.com/paper/2601.11508/) (2026)
- [ChangingGrounding: 3D Visual Grounding in Changing Scenes](https://mlsanity.com/paper/2510.14965/) (2025)
- [ShelfChange3D: Object-Level 3D Change Detection for Retail Shelf Monitoring](https://mlsanity.com/paper/2610.01283/) (2026)

## Abstract (arXiv)

AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We propose a 3D object discovery method that is based only on scene changes. Our method does not need to encode any assumptions about what is an object, but rather discovers objects by exploiting their coherent move. Changes are initially detected as differences in the depth maps and segmented as objects if they undergo rigid motions. A graph cut optimization propagates the changing labels to geometrically consistent regions. Experiments show that our method achieves state-of-the-art performance on the 3RScan dataset against competitive baselines. The source code of our method can be found at https://github.com/katadam/ObjectsCanMove.