Generative Texture Filtering

2026-04-20

AI Summary

This work addresses the longstanding challenge in texture removal tasks—balancing structural preservation with effective texture elimination—particularly in complex scenes where conventional methods struggle. To this end, it introduces, for the first time, the powerful image priors of pretrained generative models into this domain and proposes a two-stage fine-tuning strategy: first performing supervised fine-tuning on a small set of paired data, followed by reinforcement fine-tuning on large-scale unlabeled data using a carefully designed reward function. Requiring minimal annotated data, the approach seamlessly integrates supervised learning with unsupervised optimization. Extensive experiments demonstrate that the method significantly outperforms existing techniques across multiple benchmarks, achieving superior texture removal, excellent structural fidelity, and strong generalization capability.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Unsupervised & Self-Supervised Learning
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• texture filtering
• image prior
• structure preservation
• texture removal

Innovation

• generative texture filtering
• pre-trained generative models
• two-stage fine-tuning
• reinforcement learning
• image prior