# Has Anything Changed? 3D Change Detection by 2D Segmentation Masks

arXiv: https://arxiv.org/abs/2312.01148 · HTML: https://mlsanity.com/paper/2312.01148/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 2 Dec 2023.

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

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [ABO: Dataset and Benchmarks for Real-World 3D Object Understanding](https://mlsanity.com/paper/2110.06199/) (2021)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild](https://mlsanity.com/paper/2207.10660/) (2022)
- [MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects](https://mlsanity.com/paper/1804.09194/) (2018)
- [Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion](https://mlsanity.com/paper/2306.04633/) (2023)
- [Discovering Objects that Can Move](https://mlsanity.com/paper/2203.10159/) (2022)
- [ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments](https://mlsanity.com/paper/2103.05368/) (2021)
- [Object Discovery from Motion-Guided Tokens](https://mlsanity.com/paper/2303.15555/) (2023)
- [The Change You Want to See (Now in 3D)](https://mlsanity.com/paper/2308.10417/) (2023)
- [A Generalization of Otsu's Method and Minimum Error Thresholding](https://mlsanity.com/paper/2007.07350/) (2020)
- [Nothing Stands Still: A Spatiotemporal Benchmark on 3D Point Cloud Registration Under Large Geometric and Temporal Change](https://mlsanity.com/paper/2311.09346/) (2023)
- [Objects Can Move: 3D Change Detection by Geometric Transformation Constistency](https://mlsanity.com/paper/2208.09870/) (2022)
- [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, 4 of 4)

- [ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes](https://mlsanity.com/paper/2601.11508/) (2026)
- [Is there anything left? Measuring semantic residuals of objects removed from 3D Gaussian Splatting](https://mlsanity.com/paper/2503.17574/) (2025)
- [LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates](https://mlsanity.com/paper/2510.09881/) (2025)
- [ShelfChange3D: Object-Level 3D Change Detection for Retail Shelf Monitoring](https://mlsanity.com/paper/2610.01283/) (2026)

## Abstract (arXiv)

As capturing devices become common, 3D scans of interior spaces are acquired on a daily basis. Through scene comparison over time, information about objects in the scene and their changes is inferred. This information is important for robots and AR and VR devices, in order to operate in an immersive virtual experience. We thus propose an unsupervised object discovery method that identifies added, moved, or removed objects without any prior knowledge of what objects exist in the scene. We model this problem as a combination of a 3D change detection and a 2D segmentation task. Our algorithm leverages generic 2D segmentation masks to refine an initial but incomplete set of 3D change detections. The initial changes, acquired through render-and-compare likely correspond to movable objects. The incomplete detections are refined through graph optimization, distilling the information of the 2D segmentation masks in the 3D space. Experiments on the 3Rscan dataset prove that our method outperforms competitive baselines, with SoTA results.