CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929399310319616 |
|---|---|
| author | Xu, Wei Luo, Junjie Guo, Qi |
| author_facet | Xu, Wei Luo, Junjie Guo, Qi |
| contents | We present CT-Bound, a robust and fast boundary detection method for very noisy images using a hybrid Convolution and Transformer neural network. The proposed architecture decomposes boundary estimation into two tasks: local detection and global regularization. During the local detection, the model uses a convolutional architecture to predict the boundary structure of each image patch in the form of a pre-defined local boundary representation, the field-of-junctions (FoJ). Then, it uses a feed-forward transformer architecture to globally refine the boundary structures of each patch to generate an edge map and a smoothed color map simultaneously. Our quantitative analysis shows that CT-Bound outperforms the previous best algorithms in edge detection on very noisy images. It also increases the edge detection accuracy of FoJ-based methods while having a 3-time speed improvement. Finally, we demonstrate that CT-Bound can produce boundary and color maps on real captured images without extra fine-tuning and real-time boundary map and color map videos at ten frames per second. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16494 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks Xu, Wei Luo, Junjie Guo, Qi Computer Vision and Pattern Recognition We present CT-Bound, a robust and fast boundary detection method for very noisy images using a hybrid Convolution and Transformer neural network. The proposed architecture decomposes boundary estimation into two tasks: local detection and global regularization. During the local detection, the model uses a convolutional architecture to predict the boundary structure of each image patch in the form of a pre-defined local boundary representation, the field-of-junctions (FoJ). Then, it uses a feed-forward transformer architecture to globally refine the boundary structures of each patch to generate an edge map and a smoothed color map simultaneously. Our quantitative analysis shows that CT-Bound outperforms the previous best algorithms in edge detection on very noisy images. It also increases the edge detection accuracy of FoJ-based methods while having a 3-time speed improvement. Finally, we demonstrate that CT-Bound can produce boundary and color maps on real captured images without extra fine-tuning and real-time boundary map and color map videos at ten frames per second. |
| title | CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.16494 |