AdaContour: Adaptive Contour Descriptor with Hierarchical Representation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910407537459200 |
|---|---|
| author | Ding, Tianyu Zhou, Jinxin Chen, Tianyi Zhu, Zhihui Zharkov, Ilya Liang, Luming |
| author_facet | Ding, Tianyu Zhou, Jinxin Chen, Tianyi Zhu, Zhihui Zharkov, Ilya Liang, Luming |
| contents | Existing angle-based contour descriptors suffer from lossy representation for non-starconvex shapes. By and large, this is the result of the shape being registered with a single global inner center and a set of radii corresponding to a polar coordinate parameterization. In this paper, we propose AdaContour, an adaptive contour descriptor that uses multiple local representations to desirably characterize complex shapes. After hierarchically encoding object shapes in a training set and constructing a contour matrix of all subdivided regions, we compute a robust low-rank robust subspace and approximate each local contour by linearly combining the shared basis vectors to represent an object. Experiments show that AdaContour is able to represent shapes more accurately and robustly than other descriptors while retaining effectiveness. We validate AdaContour by integrating it into off-the-shelf detectors to enable instance segmentation which demonstrates faithful performance. The code is available at https://github.com/tding1/AdaContour. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08292 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AdaContour: Adaptive Contour Descriptor with Hierarchical Representation Ding, Tianyu Zhou, Jinxin Chen, Tianyi Zhu, Zhihui Zharkov, Ilya Liang, Luming Computer Vision and Pattern Recognition Graphics Existing angle-based contour descriptors suffer from lossy representation for non-starconvex shapes. By and large, this is the result of the shape being registered with a single global inner center and a set of radii corresponding to a polar coordinate parameterization. In this paper, we propose AdaContour, an adaptive contour descriptor that uses multiple local representations to desirably characterize complex shapes. After hierarchically encoding object shapes in a training set and constructing a contour matrix of all subdivided regions, we compute a robust low-rank robust subspace and approximate each local contour by linearly combining the shared basis vectors to represent an object. Experiments show that AdaContour is able to represent shapes more accurately and robustly than other descriptors while retaining effectiveness. We validate AdaContour by integrating it into off-the-shelf detectors to enable instance segmentation which demonstrates faithful performance. The code is available at https://github.com/tding1/AdaContour. |
| title | AdaContour: Adaptive Contour Descriptor with Hierarchical Representation |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2404.08292 |