# Estimating Appearance Models for Image Segmentation via Tensor Factorization

arXiv: https://arxiv.org/abs/2208.07853 · HTML: https://mlsanity.com/paper/2208.07853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 39 references that are in the map.
- First posted on arXiv 16 Aug 2022.

## Builds on (most cited first, 8 of 8)

- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Mumford-Shah Loss Functional for Image Segmentation with Deep Learning](https://mlsanity.com/paper/1904.02872/) (2019)
- [Deep GrabCut for Object Selection](https://mlsanity.com/paper/1707.00243/) (2017)
- [Tensor Factorization via Matrix Factorization](https://mlsanity.com/paper/1501.07320/) (2015)
- [PolSF: PolSAR image dataset on San Francisco](https://mlsanity.com/paper/1912.07259/) (2019)
- [Model-based learning of local image features for unsupervised texture segmentation](https://mlsanity.com/paper/1708.00180/) (2017)
- [Direct Estimation of Appearance Models for Segmentation](https://mlsanity.com/paper/2102.11121/) (2021)
- [Hierarchical Methods of Moments](https://mlsanity.com/paper/1810.07468/) (2018)

## Abstract (arXiv)

Image Segmentation is one of the core tasks in Computer Vision and solving it often depends on modeling the image appearance data via the color distributions of each it its constituent regions. Whereas many segmentation algorithms handle the appearance models dependence using alternation or implicit methods, we propose here a new approach to directly estimate them from the image without prior information on the underlying segmentation. Our method uses local high order color statistics from the image as an input to tensor factorization-based estimator for latent variable models. This approach is able to estimate models in multiregion images and automatically output the regions proportions without prior user interaction, overcoming the drawbacks from a prior attempt to this problem. We also demonstrate the performance of our proposed method in many challenging synthetic and real imaging scenarios and show that it leads to an efficient segmentation algorithm.