TL;DR
This paper introduces a generative texture filtering method that leverages pre-trained models and a two-stage fine-tuning process, achieving superior performance and generalizability in texture removal tasks.
Contribution
It proposes a novel two-stage fine-tuning strategy for pre-trained generative models to enhance texture filtering capabilities.
Findings
Outperforms previous texture filtering methods.
Effective on challenging cases of texture removal.
Utilizes a combined supervised and reinforcement fine-tuning approach.
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
