Adaptive Manifolds for Real-Time High-Dimensional Filtering
Adaptive Manifolds for Real-Time High-Dimensional Filtering
复制标题
DOI：
10.1145/2185520.2185529
复制
发表时间：
2012-07-01
影响因子：
6.2
通讯作者：
Oliveira, Manuel M.
中科院分区：
文献类型：
--
作者：
Gastal, Eduardo S. L.;Oliveira, Manuel M.
我们提出了一种技术，用于执行高维滤波的图像和视频在真实的时间。我们的方法产生高质量的结果，并通过计算滤波器的响应在一组减少的采样点，并使用这些插值在所有N个输入像素加速过滤。我们表明，对于这些采样点的适当选择，过滤操作的总成本是线性的N和在维度D的空间中，过滤器操作。因此，我们的是第一个具有如此复杂性的高维滤波器。我们提出了正式的推导方程，定义我们的过滤器，以及计算采样点的算法。这为我们的方法及其性质提供了合理的理论依据。由此产生的过滤器是相当灵活的，能够产生的响应，近似于标准的高斯，双边，或非本地均值滤波器。这种灵活性也使我们能够证明第一个混合欧几里得测地线滤波器，运行在一个单一的通道。我们的过滤器比以前的方法更快，需要更少的内存，能够在现代GPU上以50 fps的速度处理1000万像素的全色图像。我们通过执行各种任务来说明我们的方法的有效性，这些任务包括5-D中的边缘感知颜色过滤，降噪（使用多达147个维度），单通道混合欧几里得测地线过滤和细节增强等。
We present a technique for performing high-dimensional filtering of images and videos in real time. Our approach produces high-quality results and accelerates filtering by computing the filter's response at a reduced set of sampling points, and using these for interpolation at all N input pixels. We show that for a proper choice of these sampling points, the total cost of the filtering operation is linear both in N and in the dimension d of the space in which the filter operates. As such, ours is the first high-dimensional filter with such a complexity. We present formal derivations for the equations that define our filter, as well as for an algorithm to compute the sampling points. This provides a sound theoretical justification for our method and for its properties. The resulting filter is quite flexible, being capable of producing responses that approximate either standard Gaussian, bilateral, or non-local-means filters. Such flexibility also allows us to demonstrate the first hybrid Euclidean-geodesic filter that runs in a single pass. Our filter is faster and requires less memory than previous approaches, being able to process a 10-Megapixel full-color image at 50 fps on modern GPUs. We illustrate the effectiveness of our approach by performing a variety of tasks ranging from edge-aware color filtering in 5-D, noise reduction (using up to 147 dimensions), single-pass hybrid Euclidean-geodesic filtering, and detail enhancement, among others.