61,024 Hits in 7.6 sec

Fast Mesh-Based Medical Image Registration [chapter]

Ahmadreza Baghaie, Zeyun Yu, Roshan M. D'souza
2014 Lecture Notes in Computer Science  
Having Template and Reference images as inputs, the template image is triangulated using a content adaptive mesh generation algorithm.  ...  Considering the pixel values at mesh nodes, interpolated using spline interpolation method for both of the images, the energy functional needed for image registration is minimized.  ...  Using the content adaptive mesh generation method, a mesh generated for each image in the database and then used for registration of consecutive slices in the database.  ... 
doi:10.1007/978-3-319-14364-4_1 fatcat:tw7ccqpm4vhn7pvyebotyrsvgy

FaceTuneGAN: Face Autoencoder for Convolutional Expression Transfer Using Neural Generative Adversarial Networks [article]

Nicolas Olivier, Kelian Baert, Fabien Danieau, Franck Multon, Quentin Avril
2021 arXiv   pre-print
We propose a first adaptation of image-to-image translation networks, that have successfully been used in the 2D domain, to 3D face geometry.  ...  Specifically, we design an adversarial architecture adapting the base architecture of FUNIT and using SpiralNet++ for our convolutional and sampling operations.  ...  In 2018, Lim et al. introduced SpiralNet, a new convolution operator specialized for 3D meshes [32] . Gong et al. later released SpiralNet++ to refine the approach [15] .  ... 
arXiv:2112.00532v1 fatcat:fojcjzktqvewriiagh7o5zztiq

A fast approach for accurate content-adaptive mesh generation

Yongyi Yang, M.N. Wernick, J.G. Brankov
2003 IEEE Transactions on Image Processing  
A key issue in mesh modeling is how to generate a mesh structure that well represents an image by adapting to its content.  ...  In this paper we propose a new approach to mesh generation, which is based on a theoretical result derived on the error bound of a mesh representation.  ...  ., for providing the program code for Garcia's method.  ... 
doi:10.1109/tip.2003.812757 pmid:18237961 fatcat:3ri6fn4wpvb5ljpjfnwuihaei4

A Novel Semantics and Feature Preserving Perspective for Content Aware Image Retargeting [article]

Sukrit Shankar, Pier Luigi Dragotti
2015 arXiv   pre-print
There is an increasing requirement for efficient image retargeting techniques to adapt the content to various forms of digital media.  ...  Thus, there occurs a need for resizing the images in a content aware manner which can automatically discard irrelevant information from the image and present the salient features with more magnitude.  ...  Dragotti for extending his support, valuable suggestions and guidance during the entire course of this dissertation.  ... 
arXiv:1506.04806v3 fatcat:obash7smangtlopnt3jmivpu2m

Finite Element Image Warping

Peter Kaufmann, Oliver Wang, Alexander Sorkine-Hornung, Olga Sorkine-Hornung, Aljoscha Smolic, Markus Gross
2013 Computer graphics forum (Print)  
Abstract We introduce a single unifying framework for a wide range of content-aware image warping tasks using a finite element method (FEM).  ...  a b c d e Figure 1: Our unifying representation of image warping supports efficient adaptive meshing, high order basis functions, and more. a) Original image, b) automatic saliency map, c) uniform scaling  ...  Acknowledgments We would like to thank Manuel Lang for helpful discussions and Feng Liu for providing a comparison to his stabilization method.  ... 
doi:10.1111/cgf.12023 fatcat:7233lqa7crhbnca2wkc3hmrefa

Active mesh texture coding based on warping and DCT

H. Benoit-Cattin, P. Joachimsmann, A. Planat, S. Valette, A. Baskurt, R. Prost
1999 Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)  
Here, we propose a new quantiztion scheme which associates image warping and an adaptive JPEG scheme. Our approach leads to an interesting trade-off between mesh complexity and image quality.  ...  Active mesh algorithms which have been developed for region based video coding mainly use interpolation techniques to quantize the cell texture.  ...  Acknowledgments This work is in the scope of the scientific topics of the PRC-GdR ISIS research group of the French National Center for Scientific Research CNRS.  ... 
doi:10.1109/icip.1999.823013 dblp:conf/icip/Benoit-CattinJPVBP99 fatcat:b5dokdswirfz3ld5bokypz2xxy

Mesh generation and optimization from digital rock fractures based on neural style transfer

Mengsu Hu, Jonny Rutqvist, Carl I. Steefel
2021 Journal of Rock Mechanics and Geotechnical Engineering  
In this paper, we make use of neural style transfer (NST), a machine learning technique, to generate mesh from rock fracture images.  ...  We utilize the NST to generate meshes for rough fractures with asperities formed in rock, a network of fractures embedded in rock, and a sand aggregate with multiple grains.  ...  Acknowledgments The first author would like to thank Andrew Ng for teaching the enlightening online courses including Machine Learning, Neural Networks and Deep Learning, Convolutional Neural Networks,  ... 
doi:10.1016/j.jrmge.2021.02.002 fatcat:li275noyv5e2jjgrlhwj5gy5eu

Going beyond Free Viewpoint: Creating Animatable Volumetric Video of Human Performances

Anna Hilsmann, Philipp Fechteler, Wieland Morgenstern, Wolfgang Paier, Ingo Feldmann, Oliver Schreer, Peter Eisert
2020 IET Computer Vision  
In this paper, we present an end-to-end pipeline for the creation of high-quality animatable volumetric video content of human performances.  ...  This paper covers the full pipeline from capturing and producing high-quality video content, over the enrichment with semantics and deformation properties for re-animation and processing of the data for  ...  We thank the Volucap GmbH for providing the Josh sequence that was recorded for the MagentaVR app.  ... 
doi:10.1049/iet-cvi.2019.0786 fatcat:dgwxorvbf5dwlied654zxs35de

Conditional entropy maximization for PET image reconstruction using adaptive mesh model

Hongqing Zhu, Huazhong Shu, Jian Zhou, Xiubin Dai, Limin Luo
2007 Computerized Medical Imaging and Graphics  
The advantage of using the adaptive mesh model for image reconstruction is that it provides a natural spatially adaptive smoothness mechanism.  ...  In this paper, we propose a new algorithm to reconstruct an image from the PET emission projection data by using the conditional entropy maximization and the adaptive mesh model.  ...  Acknowledgements This work was supported by National Basic Research Program of China under grant No. 2003CB716102 and Program for New Century Excellent Talents in University under grant No.  ... 
doi:10.1016/j.compmedimag.2007.01.001 pmid:17368841 fatcat:saf446w2vja4vf3jth5oku7jja

User Controllable Content Retargeting and Depth Adaptation for Stereoscopic Display

Feng Shao, Libo Shen, Qiuping Jiang, Fucui Li, Yo-Sung Ho
2019 IEEE Access  
This paper presents a content retargeting and depth adaptation method for the stereoscopic image.  ...  Toward this end, we proposed a warping framework that takes content retargeting, depth adaptation, and interactive editing into account simultaneously for stereoscopic images.  ...  for those spatially important content; 2) adapts new viewing configuration with adjustable depth; and 3) leaves the space for user to edit the important content for interactive applications.  ... 
doi:10.1109/access.2019.2892098 fatcat:s6nipzzbuzcwhay26eredtn2dq

A low bit-rate video codec based on two-dimensional mesh motion compensation with adaptive interpolation

Pohsiang Hsu, K.J. Ray Liu, T. Chen
2001 IEEE transactions on circuits and systems for video technology (Print)  
The approach is to selectively break the smoothness constraint of 2-D mesh for patches that contain motion boundaries by changing the interpolation patterns.  ...  In contrast, 2-D mesh motion compensation produces blocking free prediction by generating a smooth full motion field from the set of node motion vectors using spatial interpolation.  ...  One promising approach to remedy this problem is to use a 2-D mesh-based motion estimation and compensation based on image warping.  ... 
doi:10.1109/76.894293 fatcat:hhznxkf23nbe3mgzrnzpx6s26m

Two- versus three-dimensional object-based video compression

A.M. Tekalp, Y. Altunbasak, G. Bozdagi
1997 IEEE transactions on circuits and systems for video technology (Print)  
Furthermore, experiments indicate that a 2-D mesh-based coder-decoder performs favorably compared to the new H.263 standard in terms of visual quality.  ...  We show that 2-D object-based coding with affine/perspective transformations and triangular mesh models can simulate almost all capabilities of 3-D object-based approaches using wireframe models at a fraction  ...  A content-based (adaptive) mesh is generated for the zeroth frame (shown in Fig. 6 ) which is then tracked frame-toframe using the algorithm described in Section III.  ... 
doi:10.1109/76.564115 fatcat:cq3dnvjv3zb4ndhdstljoktxxi

Improving the visual quality of AVC/H.264 by combining it with content adaptive depth map compression

Christian Keimel, Klaus Diepold, Michel Sarkis
2010 28th Picture Coding Symposium  
We present in this work a content adaptive depth map meshing with tritree and entropy encoding for 3D videos.  ...  Index Terms-AVC/H.264, 3D scene analysis, 3DTV, depth map compression, content adaptive meshing.  ...  DEPTH MAP COMPRESSION Our approach for depth map compression is composed of two parts. Firstly, the depth map is approximated with a content adaptive mesh.  ... 
doi:10.1109/pcs.2010.5702545 dblp:conf/pcs/KeimelDS10 fatcat:wspd3f3zwnhk7chusej6ef2wdq

Adaptive View Sampling for Efficient Synthesis of 3D View Using Calibrated Array Cameras

Geonwoo Kim, Deokwoo Lee
2021 Electronics  
This work aims to propose an approach to adaptive view selection (AVS) that determines the optimal number of images to generate the synthesis result using the 3D mesh and textures in terms of computational  ...  This work determines the optimal number of images that sufficiently provides a reliable 3D extended view by generating a mesh and image textures.  ...  This approach is more efficient than the approach that generates a new depth map from a synthesized color image.  ... 
doi:10.3390/electronics10010082 fatcat:nkcxjmh23rcgrorlmoodperiyi

Parallel rendering of 3D AMR data on the SGI/Cray T3E

Kwan-Liu Ma
1999 Proceedings. Frontiers '99. Seventh Symposium on the Frontiers of Massively Parallel Computation  
In this work, we compare the performance and storage requirements of a parallel volume renderer for regular-mesh data with a new parallel renderer based on adaptive sampling.  ...  AMR is a simple and powerful tool for modeling many important scientific and engineering problems. However, visualization tools for 3D AMR data are not generally available.  ...  The author would also like to thank Michael Gross and Dan Spicer at Goddard for providing the datasets and discussion of the visualization requirements for AMR data, Ming-Yun Shih for writing the program  ... 
doi:10.1109/fmpc.1999.750593 fatcat:rbyx4kwirzftplfhdrhbk57nge
« Previous Showing results 1 — 15 out of 61,024 results