Proposes LHE, SRB, and AFL components in a semantics-first latent framework that yields better 3D MRI reconstruction and cross-contrast synthesis on two public datasets.
arXiv preprint arXiv:2601.10124 (2026)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SegDINO adds Token Pyramid Adaptation and Scale-Aware Decoding to DINOv3 to deliver efficient state-of-the-art medical image segmentation on a new pancreatic CT dataset and public benchmarks.
citing papers explorer
-
Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis
Proposes LHE, SRB, and AFL components in a semantics-first latent framework that yields better 3D MRI reconstruction and cross-contrast synthesis on two public datasets.
-
SegDINO: Introducing Multi-Scale Structure into DINO for Efficient Medical Image Segmentation
SegDINO adds Token Pyramid Adaptation and Scale-Aware Decoding to DINOv3 to deliver efficient state-of-the-art medical image segmentation on a new pancreatic CT dataset and public benchmarks.