Topic
Bicubic interpolation
About: Bicubic interpolation is a research topic. Over the lifetime, 3348 publications have been published within this topic receiving 73126 citations.
Papers published on a yearly basis
Papers
More filters
01 May 1998
TL;DR: This paper considers the interpolation of fuzzy data by fuzzy-valued natural splines by giving the numerical solutions of the illustrative examples.
Abstract: In this paper, we will consider the interpolation of fuzzy data by fuzzy-valued natural splines. Finally, we will give the numerical solutions of the illustrative examples.
36 citations
30 Apr 1997
TL;DR: This unitied solution to handle usuestricted quadtrees and T-vertices, and allows for the generation of multiple different levels-of-detail of the radiosity function, which are represented as texture maps.
Abstract: Wepresenta method to speed up walkthmttghs of static scenes. It involves the cmatiort of acmttimsous C1 radiosity reconstruction for adaptively sampled tegiotts. This mpmaentation is a unitied solution to handle usuestricted quadtrees and T-vertices, and allows for the generation of multiple different levels-of-detail of the radiosity function, which are represented as texture maps. The method also involves the use of hardwase bicublc filtering for the mdiosity shading. Both techniques allow improvenmts in performance and memory usage while preserving visual appearance. CR CMegories and Subject Deaeriptom: L3.3 [Computer Graphics]: Pictusdmage Generation Viewing Algorithm, 1.3.6 [Computer Graphics]: Methodology and Techniques Integration Techniques. Additioatsl
36 citations
[...]
36 citations
TL;DR: This paper removed the bicubic interpolation operation which is handcraft up-sampling and not intelligent enough and introduced deconvolution layer instead of up-Sampling layer and designed the local polymorphic parallel network and many-to-many connections.
Abstract: In recent years, artificial intelligence has drawn the attention of the world, and the contributions of deep learning is enormous. The convolution neural network (CNN) provides more opportunities and better choices for our work. This paper explores the potential of deep neural networks in single image super-resolution (SR). In fact, some models based on deep neural networks have achieved remarkable performance in the reconstruction accuracy of individual images, but there is more room for development. In this paper, we removed the bicubic interpolation operation which is handcraft up-sampling and not intelligent enough. And we introduced deconvolution layer instead of up-sampling layer. In addition, we designed the local polymorphic parallel network and many-to-many connections. On the basis of this theory, we have carried out a simulation experiment to prove the excellent effectiveness of the proposed method.
36 citations