Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation

Wonhui Park, Dongkwon Jin, Chang-Su Kim; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 2667-2675

Abstract


Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries in a training set. Second, we decompose the contour matrix into eigencontours via the best rank-M approximation. Third, we represent an object boundary by a linear combination of the M eigencontours. We also incorporate the eigencontours into an instance segmentation framework. Experimental results demonstrate that the proposed eigencontours can represent object boundaries more effectively and more efficiently than existing descriptors in a low-dimensional space. Furthermore, the proposed algorithm yields meaningful performances on instance segmentation datasets.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Park_2022_CVPR, author = {Park, Wonhui and Jin, Dongkwon and Kim, Chang-Su}, title = {Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2667-2675} }