Unlike 2D raster images, there is no single dominant representation for 3D visual data processing. Different formats like point clouds, meshes, or implicit functions each have their strengths and weaknesses. Still, grid representations such as signed distance functions have attractive properties also in 3D. In particular, they offer constant-time random access and are eminently suitable for modern machine learning. Unfortunately, the storage size of a grid grows exponentially with its dimension. Hence they often exceed memory limits even at moderate resolution. This work proposes using low-rank tensor formats, including the Tucker, tensor train, and quantics tensor train decompositions, to compress time-varying 3D data. Our method iteratively computes, voxelizes, and compresses each frame's truncated signed distance function and applies tensor rank truncation to condense all frames into a single, compressed tensor that represents the entire 4D scene. We show that low-rank tensor compression is extremely compact to store and query time-varying signed distance functions. It significantly reduces the memory footprint of 4D scenes while remarkably preserving their geometric quality. Unlike existing, iterative learning-based approaches like DeepSDF and NeRF, our method uses a closed-form algorithm with theoretical guarantees.
翻译:与 2D 光栅图像不同, 3D 视觉数据处理没有单一的主要代表。 不同的格式, 如点云、 模shes 或隐含函数, 都有其优点和弱点。 尽管如此, 签名的远程函数等网格表示也具有3D 的吸引力。 特别是, 它们提供恒定时间随机访问, 并且非常适合现代机器学习 。 不幸的是, 网格的存储大小随其维度而成的指数指数指数成倍增长 。 因此, 即使在中等分辨率时, 它们往往超过记忆限度 。 这项工作提议使用低级的 Exor 格式, 包括塔克、 高压列车和 Quartical Exronor 列列变异配置, 以压缩时间变异 3D 数据压缩 。 我们的方法是迭接式拼凑, 并压缩每个框架的连接的远程功能。 我们的方法是迭接式拼凑, 并应用 数级变换码法将所有框架压缩成一个代表整个 4DF 。 我们显示, 低级的调调调调压压压压压非常紧紧, 以储存和变换时间的距离功能 。