Current IssuePrevious Issue  

Volume 4 No. 3
05 September 2018

Rachele Bellini, Yanir Kleiman, Daniel Cohen-Or

2018, 04(03): 197-208.   doi:10.1007/s41095-018-0115-y
Abstract ( 295 HTML ( 12   PDF(2133KB) ( 90 )   Save

In this paper we introduce a video post-processing method that enhances the rhythm of a dancing performance, in the sense that the dancing movements are more in time to the beat of the music. The dancing performance as observed in a video is analyzed and segmented into motion intervals delimited by motion beats. We present an image-space method to extract the motion beats of a video by detecting frames at which there is a significant change in direction or motion stops. The motion beats are t...

Yongwei Miao, Yuliang Sun, Xudong Fang, Jiazhou Chen, Xudong Zhang, Renato Pajarola

2018, 04(03): 209-221.   doi:10.1007/s41095-018-0111-2
Abstract ( 186 HTML ( 3   PDF(2649KB) ( 67 )   Save

Typically, relief generation from an input 3D scene is limited to either bas-relief or high-relief modeling. This paper presents a novel unified scheme for synthesizing reliefs guided by the geometric texture richness of 3D scenes; it can generate both bas- and high-reliefs. The type of relief and compression coefficient can be specified according to the user’s artistic needs. We use an energy minimization function to obtain the surface reliefs, which contains a geometry preservation term and...

Takahiro Sato, Christopher Batty, Takeo Igarashi, and Ryoichi Ando

2018, 04(03): 223-230.   doi:10.1007/s41095-018-0117-9
Abstract ( 195 HTML ( 3   PDF(1210KB) ( 72 )   Save

We introduce a new advection scheme for fluid animation. Our main contribution is the use of long-term temporal changes in pressure to extend the commonly used semi-Lagrangian scheme further back along the time axis. Our algorithm starts by tracing sample points along a trajectory following the velocity field backwards in time for many steps. During this backtracing process, the pressure gradient along the path is integrated to correct the velocity of the current time step. We show that our m...

Zhen Wei, Yao Sun, Junyu Lin, Si Liu

2018, 04(03): 231-244.   doi:10.1007/s41095-018-0112-1
Abstract ( 214 HTML ( 0   PDF(2242KB) ( 81 )   Save

In this paper, we introduce a novel approach to automatically regulate receptive fields in deep image parsing networks.?Unlike previous work which placed much importance on obtaining better receptive fields using manually selected dilated convolutional kernels, our approach uses two affine transformation layers in the network’s backbone and operates on feature maps.?Feature maps are inflated or shrunk by the new layer, thereby changing the receptive fields in the following layers.?By use of e...

Kai-Xuan Chen, Xiao-Jun Wu

2018, 04(03): 245-252.   doi:10.1007/s41095-018-0119-7
Abstract ( 210 HTML ( 0   PDF(594KB) ( 83 )   Save

In pattern recognition, the task of image set classification has often been performed by representing data using symmetric positive definite (SPD) matrices, in conjunction with the metric of the resulting Riemannian manifold.?In this paper, we propose a new data representation framework for image sets which we call component symmetric positive definite representation (CSPD). Firstly, we obtain sub-image sets by dividing the images in the set into square blocks of the same size, and use...

Yifan Lu, Jiaming Lu, Songhai Zhang, Peter Hall

2018, 04(03): 253-266.   doi:10.1007/s41095-018-0116-x
Abstract ( 294 HTML ( 1   PDF(2176KB) ( 138 )   Save

Abstract??Detecting small objects is a challenging task.?We focus on a special case:?the detection and classification of traffic signals in street views.?We present a novel framework that utilizes a visual attention model to make detection more efficient, without loss of accuracy, and which generalizes. The attention model is designed to generate a small set of candidate regions at a suitable scale so that small targets can be better located and classified. In order to evaluate our method in ...

Matias K. Koskela, Kalle V. Immonen, Timo T. Viitanen, Pekka O. Jääskeläinen, Joonas I. Multanen, Jarmo H. Takala

2018, 04(03): 267-276.   doi:10.1007/s41095-018-0113-0
Abstract ( 160 HTML ( 0   PDF(3232KB) ( 64 )   Save

Progressive rendering, for example Monte Carlo rendering of 360 content for virtual reality headsets, is a time-consuming task.?If the 3D artist notices an error while previewing the rendering, they must return to editing mode, make the required changes, and restart rendering.?We propose the use of eye-tracking-ba...

Jesse Archer, Geoff Leach, Ron van Schyndel

2018, 04(03): 277-285.   doi:10.1007/s41095-018-0118-8
Abstract ( 207 HTML ( 0   PDF(1338KB) ( 72 )   Save

Deep images store multiple fragments per-pixel, each of which includes colour and depth, unlike traditional 2D flat images which store only a single colour value and possibly a depth value.?Recently, deep images have found use in an increasing number of applications, including ones using transparency and compositing.?A step in compositing deep images requires merging per-pixel fragment lists in depth order; little work has so far been presented on fast approaches.

This paper explores GP...