CT-Bound: Robust Boundary Detection From Noisy Images Via Hybrid Convolution and Transformer Neural Networks
This addresses the problem of accurate and fast boundary detection in noisy images for computer vision applications, representing a strong incremental advance over existing methods.
The paper tackles robust boundary detection from very noisy images using a hybrid Convolution and Transformer neural network, achieving state-of-the-art edge detection accuracy with a 3-time speed improvement and real-time processing at ten frames per second.
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.