# Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data

arXiv: https://arxiv.org/abs/1509.02649 · HTML: https://mlsanity.com/paper/1509.02649/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Sep 2015.

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

- [Quantum Motion Segmentation](https://mlsanity.com/paper/2203.13185/) (2022)
- [Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering](https://mlsanity.com/paper/2106.09874/) (2021)
- [A Simple Approach to Automated Spectral Clustering](https://mlsanity.com/paper/2107.12183/) (2021)
- [Latent Semantic Consensus For Deterministic Geometric Model Fitting](https://mlsanity.com/paper/2403.06444/) (2024)
- [Learning To Segment Dominant Object Motion From Watching Videos](https://mlsanity.com/paper/2111.14160/) (2021)
- [Attentive Multi-View Deep Subspace Clustering Net](https://mlsanity.com/paper/2112.12506/) (2021)
- [Reconstructing Small 3D Objects in front of a Textured Background](https://mlsanity.com/paper/2105.11352/) (2021)
- [On Matrix Factorizations in Subspace Clustering](https://mlsanity.com/paper/2106.12016/) (2021)

## Abstract (arXiv)

The Shape Interaction Matrix (SIM) is one of the earliest approaches to performing subspace clustering (i.e., separating points drawn from a union of subspaces). In this paper, we revisit the SIM and reveal its connections to several recent subspace clustering methods. Our analysis lets us derive a simple, yet effective algorithm to robustify the SIM and make it applicable to realistic scenarios where the data is corrupted by noise. We justify our method by intuitive examples and the matrix perturbation theory. We then show how this approach can be extended to handle missing data, thus yielding an efficient and general subspace clustering algorithm. We demonstrate the benefits of our approach over state-of-the-art subspace clustering methods on several challenging motion segmentation and face clustering problems, where the data includes corrupted and missing measurements.