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: International confer- ence on machine learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
SpectraDINO adapts frozen DINOv2 backbones to multispectral data via per-modality adapters and staged distillation with cosine, contrastive, patch, and neighborhood-structure losses, achieving SOTA on object detection and segmentation benchmarks.
The paper presents the first generative photomosaic framework that synthesizes tiles via structure-aligned diffusion models and few-shot personalization instead of color-based matching from large tile collections.
VLMs caption real objects effectively but degrade on 3D-printed fakes in robotic scenes, while some standard metrics fail to detect the factual errors from this domain shift.