CAFlow：自适应深度单步流匹配用于高效组织病理学超分辨率
CAFlow: Adaptive-Depth Single-Step Flow Matching for Efficient Histopathology Super-Resolution
AI总结：
CAFlow通过自适应路由机制实现高效组织病理学超分辨率，利用单步流匹配框架在减少计算量的同时提升重建质量，实验显示其在不同放大倍数下均优于现有方法。
摘要：
在数字病理学中，整张滑片图像 routinely 超过十亿像素分辨率，使得计算密集型生成超分辨率（SR）在常规部署中不现实。我们介绍了CAFlow，一种自适应深度单步流匹配框架，将每个图像块路由到能保持重建质量的最浅网络出口。CAFlow在像素未shuffle的重新排列空间中进行流匹配，将空间计算减少16倍，同时允许直接推断。我们显示，将一半的训练分配给精确t=0样本对于单步质量至关重要（没有它会下降1.5 dB）。骨干网络FlowResNet（1.90M参数）在四个早期出口中混合卷积和窗口自注意力块，覆盖3.1到13.3 GFLOPs。轻量级出口分类器（~6K参数）在仅0.12 dB的代价下实现33%的计算节省。在多器官组织病理学x4 SR中，自适应路由在全深度下的PSNR为31.84 dB，而自适应路由达到31.72 dB，最浅的出口在2.8倍的计算量下优于bicubic，且在x8放大时优于所有可比计算基线，同时与SwinIR-Medium模型竞争。下游核分割验证了临床相关结构的保留。该模型在单个GPU上训练时间不足5小时，自适应路由可将整张滑片推断时间从分钟减少到秒。
英文摘要：
In digital pathology, whole-slide images routinely exceed gigapixel resolution, making computationally intensive generative super-resolution (SR) impractical for routine deployment. We introduce CAFlow, an adaptive-depth single-step flow-matching framework that routes each image tile to the shallowest network exit that preserves reconstruction quality. CAFlow performs flow matching in pixel-unshuffled rearranged space, reducing spatial computation by 16x while enabling direct inference. We show that dedicating half of training to exact t=0 samples is essential for single-step quality (-1.5 dB without it). The backbone, FlowResNet (1.90M parameters), mixes convolution and window self-attention blocks across four early exits spanning 3.1 to 13.3 GFLOPs. A lightweight exit classifier (~6K parameters) achieves 33% compute savings at only 0.12 dB cost. On multi-organ histopathology x4 SR, adaptive routing achieves 31.72 dB PSNR versus 31.84 dB at full depth, while the shallowest exit exceeds bicubic by +1.9 dB at 2.8x less compute than SwinIR-light. The method generalizes to held-out colon tissue with minimal quality loss (-0.02 dB), and at x8 upscaling it outperforms all comparable-compute baselines while remaining competitive with the much larger SwinIR-Medium model. Downstream nuclei segmentation confirms preservation of clinically relevant structure. The model trains in under 5 hours on a single GPU, and adaptive routing can reduce whole-slide inference from minutes to seconds.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
