An MLLM-guided architecture with a mixture of frequency experts and relational alignment loss achieves state-of-the-art all-in-one image restoration, outperforming prior methods by up to 1.35 dB on the CDD11 dataset.
In: European conference on computer vision
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
DABSeg unifies motion deblurring and multimodal 3D brain tumor segmentation via a feature-domain deblurring stem, blur-aware cross-attention, and a joint weighted Dice plus reconstruction loss, showing higher Dice scores than prior methods on BraTS2020 under both clear and degraded conditions.
citing papers explorer
-
Leveraging Multimodal Large Language Models for All-in-One Image Restoration via a Mixture of Frequency Experts
An MLLM-guided architecture with a mixture of frequency experts and relational alignment loss achieves state-of-the-art all-in-one image restoration, outperforming prior methods by up to 1.35 dB on the CDD11 dataset.
-
Degradation-Aware Blur-Segmentation of Brain Tumor
DABSeg unifies motion deblurring and multimodal 3D brain tumor segmentation via a feature-domain deblurring stem, blur-aware cross-attention, and a joint weighted Dice plus reconstruction loss, showing higher Dice scores than prior methods on BraTS2020 under both clear and degraded conditions.