3 papers
cs.CV2026
MIAR: Medical Image Super-Resolution With Autoregressive Modeling
Fang Li, Yinglong Li, Hongyu Wu +3
Medical Image Super-Resolution (MISR) aims to enhance spatial resolution without requiring hardware modifications. Although deep learning has yielded promising results, existing pa…
cs.CV2026
TRCoRSurg: Temporal-Relational Co-Reasoning for Surgical Video Triplet Recognition
Fang Li, Shihao Zou, Weixin Si +3
Understanding complex surgical scenes requires recognizing multiple interdependent entities, such as instruments, actions, and targets, while maintaining their relational consisten…
cs.CV2026
VoxStruct3D: Structure-Leading Flow Matching for Voxel-Space 3D MRI Synthesis
Fang Li, Yang Gao, Shihao Zou +5
High-fidelity 3D MRI synthesis requires both globally coherent anatomy and fine-grained voxel-level detail. Although latent diffusion makes volumetric generation tractable, its ima…