Ashish Sinha, Jeremy Kawahara, Arezou Pakzad, Kumar Abhishek, Matthieu Ruthven...
TL;DR本研究提出了一种名为DermSynth3D的新型框架,它将皮肤病模式与人类主体的 3D 网格相融合,并使用可微分渲染器从不同的摄像机视点在各种背景场景下生成 2D 图像。DermSynth3D可以为各种皮肤病学任务创建自定义数据集,该数据集在训练深度学习模型时表现良好。
Abstract
In recent years, deep learning (DL) has shown great potential in the field of dermatological image analysis. However, existing datasets in this domain have significant limitations, including a small number of ima