Discontinuity-Aware 2D Neural Fields
Discontinuity-Aware 2D Neural Fields
复制标题
DOI：
10.1145/3618379
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Yash Belhe;Michaël Gharbi;Matthew Fisher;Iliyan Georgiev;Ravi Ramamoorthi;Tzu-Mao Li
中科院分区：
文献类型：
--
作者：
Yash Belhe;Michaël Gharbi;Matthew Fisher;Iliyan Georgiev;Ravi Ramamoorthi;Tzu-Mao Li
神经图像表示具有高保真度，紧凑的存储和独立于解决方案的准确性，为传统的像素和网格的表示提供了有吸引力的替代品，但是，协调神经元网络未能捕获图像中存在的不连续性，并且倾向于模糊。在许多情况下，我们旨在应对这一挑战，例如渲染图像，矢量图形，差异曲线或偏微分方程的解决方案，我们将这些位置作为线性。 ，二次或立方体曲线，并构建一个在这些位置不连续的特征字段，并在其他任何地方平滑。基于弯曲的三角形网格开发新的数据结构，并在顶点和边缘的子集上存储，并将其标记为不连续的东西。 25MB文件可以通过与基于蒙特卡洛的方法结合或通过扩散曲线能量直接监督的新扩散曲线求解器。
Neural image representations offer the possibility of high fidelity, compact storage, and resolution-independent accuracy, providing an attractive alternative to traditional pixel- and grid-based representations. However, coordinate neural networks fail to capture discontinuities present in the image and tend to blur across them; we aim to address this challenge. In many cases, such as rendered images, vector graphics, diffusion curves, or solutions to partial differential equations, the locations of the discontinuities are known. We take those locations as input, represented as linear, quadratic, or cubic Bézier curves, and construct a feature field that is discontinuous across these locations and smooth everywhere else. Finally, we use a shallow multi-layer perceptron to decode the features into the signal value. To construct the feature field, we develop a new data structure based on a curved triangular mesh, with features stored on the vertices and on a subset of the edges that are marked as discontinuous. We show that our method can be used to compress a 100, 0002-pixel rendered image into a 25MB file; can be used as a new diffusion-curve solver by combining with Monte-Carlo-based methods or directly supervised by the diffusion-curve energy; or can be used for compressing 2D physics simulation data.