AI RESEARCH

RF-HiT: Rectified Flow Hierarchical Transformer for General Medical Image Segmentation

arXiv CS.CV

ArXi:2604.19570v1 Announce Type: new Accurate medical image segmentation requires both long-range contextual reasoning and precise boundary delineation, a task where existing transformer- and diffusion-based paradigms are frequently bottlenecked by quadratic computational complexity and prohibitive inference latency. We propose RF-HiT, a Rectified Flow Hierarchical Transformer that integrates an hourglass transformer backbone with a multi-scale hierarchical encoder for anatomically guided feature conditioning.