上海科技大学知识管理系统

A method of rendering an object, the method comprising : capturing a plurality of images of the object from a plurality of views; obtaining an alpha mask for each image; obtaining a 3D proxy geometry through a structure from silhouette algorithm; rendering a depth map for each image using the 3D proxy; training a neural radiance field-based (NeRF-based) deep neural network with images with depth; and rendering a plurality of images for a plurality of new views. The method can generate photo-realistic rendering results. Particularly, an acceleration method is applied in our framework, which can speed up training and rendering processes. In addition, a patch-based training scheme is introduced, which significantly increases the quality of outputs and preserves high frequency details.

一种渲染对象的方法，所述方法包括：从多个视图捕获所述对象的多个图像； 获得每个图像的掩模； 通过来自轮廓算法的结构获得3D代理几何形状； 使用3D代理为每个图像绘制深度图； 用具有深度的图像训练基于神经辐射场(基于神经的)深度神经网络； 以及为多个新视图呈现多个图像。 该方法可以生成照片真实感渲染结果。 特别地，在我们的框架中应用了加速方法，这可以加速训练和渲染过程。 此外，引入了基于补丁的训练方案，这显著地提高了输出的质量并保留了高频细节。