Generative Texture Filtering
This work addresses the problem of texture filtering for computer vision applications, offering a more effective solution that leverages generative models to handle previously difficult scenarios.
The authors propose a generative method for texture filtering that fine-tunes a pre-trained generative model using a two-stage strategy, achieving superior performance and generalizability over previous methods, particularly in challenging cases.
We present a generative method for texture filtering, which exhibits surprisingly good performance and generalizability. Our core idea is to empower texture filtering by taking full advantage of the strong learned image prior of pre-trained generative models. To this end, we propose to fine-tune a pre-trained generative model via a two-stage strategy. Specifically, we first conduct supervised fine-tuning on a very small set of paired images, and then perform reinforcement fine-tuning on a large-scale unlabeled dataset under the guidance of a reward function that quantifies the quality of texture removal and structure preservation. Extensive experiments show that our method clearly outperforms previous methods, and is effective to deal with previously challenging cases. Our code is available at https://github.com/OnlyZZZZ/Generative_Texture_Filtering.