Iterative unsupervised deep bilateral texture filtering

Texture filtering attempts to retain salient structures and remove insignificant textures. In this paper, we propose a highly effective iterative unsupervised deep bilateral texture filtering neural network for texture smoothing. The bilateral texture loss function is introduced to train the model without the ground truth smoothing images for guidance. The proposed model inherits well-known advantages of the bilateral texture filter to capture the texture information effectively. The model is trained solely using the training data, then the predicted outputs are generated iteratively through multiple forward passes. Extensive experiments demonstrate that our proposed iterative unsupervised deep bilateral texture filtering neural network outperforms existing methods in effectively removing textures while preserving the main structures of the image. The results showcase the superior performance of our approach and its ability to achieve high-quality texture smoothing without sacrificing important image features.

Automated summary

Texture filtering technique aims to remove insignificant textures and retain important structures. In this paper, we propose an effective unsupervised deep bilateral texture filtering neural network that achieves texture smoothing. The model is trained with a bilateral texture loss function and does not require ground truth smoothing images. Extensive experiments show that our approach outperforms existing methods in effectively removing textures while preserving the main image structures.