Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guan, Kai, Wu, Rongyuan, Li, Shuai, Zhu, Wentao, Zeng, Wenjun, Zhang, Lei
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2602.14042
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915799553277952
author Guan, Kai
Wu, Rongyuan
Li, Shuai
Zhu, Wentao
Zeng, Wenjun
Zhang, Lei
author_facet Guan, Kai
Wu, Rongyuan
Li, Shuai
Zhu, Wentao
Zeng, Wenjun
Zhang, Lei
contents In real-world scenarios, the performance of semantic segmentation often deteriorates when processing low-quality (LQ) images, which may lack clear semantic structures and high-frequency details. Although image restoration techniques offer a promising direction for enhancing degraded visual content, conventional real-world image restoration (Real-IR) models primarily focus on pixel-level fidelity and often fail to recover task-relevant semantic cues, limiting their effectiveness when directly applied to downstream vision tasks. Conversely, existing segmentation models trained on high-quality data lack robustness under real-world degradations. In this paper, we propose Restoration Adaptation for Semantic Segmentation (RASS), which effectively integrates semantic image restoration into the segmentation process, enabling high-quality semantic segmentation on the LQ images directly. Specifically, we first propose a Semantic-Constrained Restoration (SCR) model, which injects segmentation priors into the restoration model by aligning its cross-attention maps with segmentation masks, encouraging semantically faithful image reconstruction. Then, RASS transfers semantic restoration knowledge into segmentation through LoRA-based module merging and task-specific fine-tuning, thereby enhancing the model's robustness to LQ images. To validate the effectiveness of our framework, we construct a real-world LQ image segmentation dataset with high-quality annotations, and conduct extensive experiments on both synthetic and real-world LQ benchmarks. The results show that SCR and RASS significantly outperform state-of-the-art methods in segmentation and restoration tasks. Code, models, and datasets will be available at https://github.com/Ka1Guan/RASS.git.
format Preprint
id arxiv_https___arxiv_org_abs_2602_14042
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Restoration Adaptation for Semantic Segmentation on Low Quality Images
Guan, Kai
Wu, Rongyuan
Li, Shuai
Zhu, Wentao
Zeng, Wenjun
Zhang, Lei
Computer Vision and Pattern Recognition
Artificial Intelligence
In real-world scenarios, the performance of semantic segmentation often deteriorates when processing low-quality (LQ) images, which may lack clear semantic structures and high-frequency details. Although image restoration techniques offer a promising direction for enhancing degraded visual content, conventional real-world image restoration (Real-IR) models primarily focus on pixel-level fidelity and often fail to recover task-relevant semantic cues, limiting their effectiveness when directly applied to downstream vision tasks. Conversely, existing segmentation models trained on high-quality data lack robustness under real-world degradations. In this paper, we propose Restoration Adaptation for Semantic Segmentation (RASS), which effectively integrates semantic image restoration into the segmentation process, enabling high-quality semantic segmentation on the LQ images directly. Specifically, we first propose a Semantic-Constrained Restoration (SCR) model, which injects segmentation priors into the restoration model by aligning its cross-attention maps with segmentation masks, encouraging semantically faithful image reconstruction. Then, RASS transfers semantic restoration knowledge into segmentation through LoRA-based module merging and task-specific fine-tuning, thereby enhancing the model's robustness to LQ images. To validate the effectiveness of our framework, we construct a real-world LQ image segmentation dataset with high-quality annotations, and conduct extensive experiments on both synthetic and real-world LQ benchmarks. The results show that SCR and RASS significantly outperform state-of-the-art methods in segmentation and restoration tasks. Code, models, and datasets will be available at https://github.com/Ka1Guan/RASS.git.
title Restoration Adaptation for Semantic Segmentation on Low Quality Images
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2602.14042