Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.02313 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917558397960192 |
|---|---|
| author | Kai, Leng Zhijie, Zhang Jie, Liu Boukhers, Zed Wei, Sui Yang, Cong Zhijun, Li |
| author_facet | Kai, Leng Zhijie, Zhang Jie, Liu Boukhers, Zed Wei, Sui Yang, Cong Zhijun, Li |
| contents | Edge detection is a fundamental technique in various computer vision tasks. Edges are indeed effectively delineated by pixel discontinuity and can offer reliable structural information even in textureless areas. State-of-the-art heavily relies on pixel-wise annotations, which are labor-intensive and subject to inconsistencies when acquired manually. In this work, we propose a novel self-supervised approach for edge detection that employs a multi-level, multi-homography technique to transfer annotations from synthetic to real-world datasets. To fully leverage the generated edge annotations, we developed SuperEdge, a streamlined yet efficient model capable of concurrently extracting edges at pixel-level and object-level granularity. Thanks to self-supervised training, our method eliminates the dependency on manual annotated edge labels, thereby enhancing its generalizability across diverse datasets. Comparative evaluations reveal that SuperEdge advances edge detection, demonstrating improvements of 4.9% in ODS and 3.3% in OIS over the existing STEdge method on BIPEDv2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_02313 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SuperEdge: Towards a Generalization Model for Self-Supervised Edge Detection Kai, Leng Zhijie, Zhang Jie, Liu Boukhers, Zed Wei, Sui Yang, Cong Zhijun, Li Computer Vision and Pattern Recognition Edge detection is a fundamental technique in various computer vision tasks. Edges are indeed effectively delineated by pixel discontinuity and can offer reliable structural information even in textureless areas. State-of-the-art heavily relies on pixel-wise annotations, which are labor-intensive and subject to inconsistencies when acquired manually. In this work, we propose a novel self-supervised approach for edge detection that employs a multi-level, multi-homography technique to transfer annotations from synthetic to real-world datasets. To fully leverage the generated edge annotations, we developed SuperEdge, a streamlined yet efficient model capable of concurrently extracting edges at pixel-level and object-level granularity. Thanks to self-supervised training, our method eliminates the dependency on manual annotated edge labels, thereby enhancing its generalizability across diverse datasets. Comparative evaluations reveal that SuperEdge advances edge detection, demonstrating improvements of 4.9% in ODS and 3.3% in OIS over the existing STEdge method on BIPEDv2. |
| title | SuperEdge: Towards a Generalization Model for Self-Supervised Edge Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.02313 |