研究人员开发了一种新颖的方法来获取和表示物体中光传输的次表面散射特性。该技术利用U-Net卷积神经网络（CNN）从3D扫描数据中学习像素足迹响应。通过采用具有相位偏移轮廓测量图案的立体投影仪-相机设置，系统捕获详细的散射数据，从而能够用任意高分辨率图案对物体进行逼真的重照明。 AI
排序理由 该集群包含一篇在arXiv上发表的研究论文，详细介绍了一种新的计算机视觉方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.02292v1 Announce Type: new Abstract: We present a method to acquire and estimate the sub-surface scattering properties of light transport at a highly detailed level by learning the pixel footprint response at each point on the object surface. The reconstruction leverag…
We present a method to acquire and estimate the sub-surface scattering properties of light transport at a highly detailed level by learning the pixel footprint response at each point on the object surface. The reconstruction leverages 3D scanning techniques as input to a U-Net CN…