Topic
Upsampling
About: Upsampling is a research topic. Over the lifetime, 2426 publications have been published within this topic receiving 57613 citations.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this article , the most informative samples in the given imbalanced dataset through the active learning strategy is selected to mitigate the effect of imbalanced class labels. But, the data selection is performed by the criterion used in optimal experimental designs, from which the generalization error of the trained model is minimized sequentially, under the penalized logistic regression as a classification model.
14 citations
••
TL;DR: In this paper , a meta-subnetwork is learned to adjust the weights of residual graph convolution (RGC) blocks dynamically, and a farthest sampling block is adopted to sample different numbers of points.
Abstract: Point cloud upsampling is vital for the quality of the mesh in three-dimensional reconstruction. Recent research on point cloud upsampling has achieved great success due to the development of deep learning. However, the existing methods regard point cloud upsampling of different scale factors as independent tasks. Thus, the methods need to train a specific model for each scale factor, which is both inefficient and impractical for storage and computation in real applications. To address this limitation, in this article, we propose a novel method called "Meta-PU" to first support point cloud upsampling of arbitrary scale factors with a single model. In the Meta-PU method, besides the backbone network consisting of residual graph convolution (RGC) blocks, a meta-subnetwork is learned to adjust the weights of the RGC blocks dynamically, and a farthest sampling block is adopted to sample different numbers of points. Together, these two blocks enable our Meta-PU to continuously upsample the point cloud with arbitrary scale factors by using only a single model. In addition, the experiments reveal that training on multiple scales simultaneously is beneficial to each other. Thus, Meta-PU even outperforms the existing methods trained for a specific scale factor only.
14 citations
•
16 Dec 2004
TL;DR: In this article, a set of source points that represent a stroke input of a user is identified, and the source points may then be refined and/or modified for decoding and reproduction of a stroke representation.
Abstract: A set of source points that represent a stroke input of a user is identified. The set of source points may be refined and/or modified. The set of refined/modified source points may then be stored in memory for decoding and recreation of a stroke representation. Additionally, one or both of refining and modifying the source points may be performed through one or more upsampling processes.
14 citations
01 Jan 2001
TL;DR: A novel modeling method is presented for beating and two-stage decay of partials, where these phenomena are most prominent, by using the multi-rate approach and taking the advantage of the characteristics of the resonators.
Abstract: In this paper a novel modeling method is presented for beating and two-stage decay. Here, one digital waveguide is used for each note and some resonators are run in parallel to simulate the beating and two-stage decay of those partials, where these phenomena are most prominent. The resonator bank is implemented by using the multi-rate approach, resulting in a decrease of computational cost by a factor of 10. By taking the advantage of the characteristics of the resonators, relatively simple upsampling and downsampling filters are used. Two different filtering approaches are presented and compared with respect to computational complexity. Examples are shown with the application to piano sound synthesis.
13 citations
••
TL;DR: A fine coregistration method for synthetic aperture radar (SAR) image processing, such as in InSAR interferogram generation, that displays superior accuracy for images with near homogeneous fractal behavior.
Abstract: This paper presents a fine coregistration method for synthetic aperture radar (SAR) image processing, such as in InSAR interferogram generation. Under the assumption that SAR images are properly modeled as fractional Brownian motion, relative subpixel offsets between two images can be derived from the statistics of their increments. The method does not require upsampling or cross-correlation, thus allowing for an accurate offset estimation with less computational load. Implemented as a local coregistration procedure, it also provides a nonrigid geometric alignment that nicely follows the topography of the area. Experimental results show that the method gives comparable results to the conventional method, in terms of the accuracy of the generated digital elevation models. In particular, it displays superior accuracy for images with near homogeneous fractal behavior.
13 citations