Joint Up-sampling High Dynamic Range Images with a Guidance Image

Abstract

In this paper, we address the problem of acquiring guidance images for use in joint up-sampling of high dynamic range (HDR) images. A guidance image is usually an unprocessed high-resolution image that is indispensable to joint up-sampling, which is aimed at accelerating a large class of image processing operators. However, the guidance image is blank-posed in joint up-sampling of the HDR image, which involves the process where multiple low dynamic range (LDR) images with various exposure times in the same scene are synthesized into one image with a greater dynamic range; Such many-toone operations limit joint up-sampling in being applied to this field. To this end, we propose an HDR guidance image (HGI), which is an image type generated by weighted averaging LDR images into a single with rich contour information. The huge advantage of joint up-sampling is that the cost of running the original algorithm is at a greatly reduced resolution. Since HGI synthesis takes about 3-70ms, and joint up-sampling of an HDR image takes about 20-300ms, most operations can be done with GPU shaders. Compared with the conventional methods of HDR image reconstruction, using joint upsampling can achieve 3-10 times the performance acceleration. We demonstrate that joint up-sampling using our guidance images can produce high-resolution HDR images with no visible degradation compared to the image produced by the conventional method.

Bézier Curves and Surfaces with three Parameters and Extensions in the Triangular Domain

“…At the same time, the triangle area curve and surface in the practical application has important value, not only to overcome Bézier curve and surface in the control of the same vertex conditions can not be flexible to adjust the shape of the shortcomings, but also to solve the irregular data points under Bézier curve and surface modeling design problems. Bézier surface of the rectangular domain is in the form of tensor product, and Bézier of the triangular domain is in the form of non-tensor product, there is a lot of literature on the rectangular domain Bézier basis function is defined for the triangular domain [12][13][14][15][16][17][18][19][20][21][22][23], which Wu Hongyi [18] et al The triangular domain B é zier with multiple shape parameters, It increases the operation difficulty of curves and surfaces. Yu Liping's [19] curved surface with two shape parameters in triangular domain can be adjusted freely, but it lacks generality.…”

Double Cubic Singular Blend Bézier Surfaces

“…Surface modeling technology is the key technology in many fields such as CAD/CAM, CG, computer animation, computer simulation, artificial intelligence [1], computer visualization, some aspects of computer image processing [2][3], and so on. In surface design, people strive to use methods to ensure that the surface has a higher smooth continuity, but also convenient and flexible, easy to control and modify the designed surface.…”

Medical Image Fusion Combining Singular Value Decomposition and Mean Gradient

“…Although the spatial resolution of the image can be improved, it is difficult to select the uncertainty of the threshold. In reference [4], it is proposed that high-frequency [19] and low-frequency components can be obtained by using wavelet transform, and then the principle of maximizing directional contrast and average gradient is applied in the neighborhood, and the corresponding fusion rules are selected to obtain the fused image which is easy to cause image distortion. In reference [5], different component matrices are obtained after singular value decomposition of source image.…”