随笔分类 - 深度学习
摘要:Learning Saliency from Scribbles
阅读全文
摘要:Volume Rendering Principle Create a two dimensional image that reflects, at every pixel, the data along a ray parallel to the viewing direction passin
阅读全文
摘要:Volume Rendering 感性理解 感性理解:三维空间划分成很多体素,每个体素有RGBA四种信息,表示颜色(RGB)和透明度(A) 要渲染二维表示,我们选定坐标原点,以它为球心发出很多射线 每条射线会穿过一些体素,我们沿着光线的路径进行颜色的加权统计(权重为不透明度) 每个体素对最终颜色会造
阅读全文
摘要:Global Context-Aware Progressive Aggregation Network for Salient Object Detection Facts due to the pyramid-like CNNs structure, high-level features he
阅读全文