8,980 Hits in 7.7 sec

Tracing ray differentials

Homan Igehy
1999 Proceedings of the 26th annual conference on Computer graphics and interactive techniques - SIGGRAPH '99  
In this paper, we present a fast, simple, robust scheme for tracking such a quantity based on ray differentials, derivatives of the ray with respect to the image plane.  ...  While this type of filtering works well for many algorithms, it is much more efficient to perform filtering locally on a surface for algorithms such as texture mapping.  ...  Acknowledgements We would like to thank Pat Hanrahan, Matthew Eldridge, Matt Pharr, Tamara Munzner, and the reviewers for their assistance with this paper.  ... 
doi:10.1145/311535.311555 dblp:conf/siggraph/Igehy99 fatcat:n4pgyrqtsrhbdfz2nu2zv2u22i

Integrated Image Matching and Segmentation for 3D Surface Reconstruction in Urban Areas

Lei Ye, Bo Wu
2018 Photogrammetric Engineering and Remote Sensing  
occlusion filtering, (2) segment-adaptive similarity measurement to reduce matching ambiguity, and (3) local and regional dense matching propagation to generate reliable and dense matches.  ...  In urban areas, however, image matching is particularly difficult because of the complexity of urban textures and the severe occlusion problems caused by buildings.  ...  Accordingly, it propagates the constraints from robust matches with favorable textures to the matching in areas with less favorable textures using triangular segmentation.  ... 
doi:10.14358/pers.84.3.135 fatcat:vtsg3u6qdzhybkuosyrq3w4bze

Improvement of vessel segmentation by elastically compensated patient motion in digital subtraction angiography images [chapter]

Thorsten M. Buzug, Cristian Lorenz, Jürgen Weese
1997 Lecture Notes in Computer Science  
Wahl 361 Improving the Shape Recognition Performance of a Model with Gabor Filter Representation P. Kalocsai 369 Bayesian Decision Versus Voting for Image Retrieval R. Mohr, S. Picard, C.  ...  Weese 106 Three-Dimensional Quasi-binary Image Restoration for Confocal Microscopy arid Its Application to Dendritic Trees A. Herzog, G. Krell, B. Michaelis, J. Wang, W. Zuschratter, K.  ... 
doi:10.1007/3-540-63460-6_106 fatcat:slrzatrulfcb3b4wmyv3zhlshu

Edge-preserving color image denoising through tensor voting

Rodrigo Moreno, Miguel Angel Garcia, Domenec Puig, Carme Julià
2011 Computer Vision and Image Understanding  
image denoising algorithms for images contaminated with CCD camera noise.  ...  This paper presents a new method for edge-preserving color image denoising based on the tensor voting framework, a robust perceptual grouping technique used to extract salient information from noisy data  ...  framework that can be adapted to a variety of applications well beyond the ones which it was originally applied to.  ... 
doi:10.1016/j.cviu.2011.07.005 fatcat:h563l35gcvbetl36bxj5yzhxw4

Temporally Coherent Video Stylization [chapter]

Pierre Bénard, Joëlle Thollot, John Collomosse
2012 Computational Imaging and Vision  
We begin with flow-based adaptations of stroke based rendering (SBR) and texture advection capable of painting video.  ...  We then chart the development of the field, and its fusion with Computer Vision, to deliver coherent mid-level scene representations.  ...  Image edges are extracted from the smoothed images with a difference of Gaussian filter.  ... 
doi:10.1007/978-1-4471-4519-6_13 fatcat:rzfrfol6erdr3bldrw4xtjt4dq

Fast Global Image Smoothing Based on Weighted Least Squares

Dongbo Min, Sunghwan Choi, Jiangbo Lu, Bumsub Ham, Kwanghoon Sohn, Minh N. Do
2014 IEEE Transactions on Image Processing  
We demonstrate the effectiveness and efficiency of our techniques in a range of image processing and computer graphics applications.  ...  ., efficient edge-preserving filters and optimization-based smoothing.  ...  Unlike the local filtering approaches [2] , [8] , [9] , the optimization-based methods are directly applicable to many tasks beyond image smoothing, which can be modeled as a linear system with an inhomogeneous  ... 
doi:10.1109/tip.2014.2366600 pmid:25373085 fatcat:e7fngjxyl5bejeahwwlusxttbi

Spatial sound for video games and virtual environments utilizing real-time GPU-based convolution

Brent Cowan, Bill Kapralos
2008 Proceedings of the 2008 Conference on Future Play Research, Play, Share - Future Play '08  
Despite the many similarities between the fields of spatial audio and computer graphics, computer graphics and image synthesis in particular, has advanced far beyond spatial audio given the emphasis placed  ...  The generation of spatial audio is computationally very demanding and therefore, accurate spatial audio is typically overlooked in games and virtual environments applications thus leading to a decrease  ...  Acknowledgments The financial support of the Natural Sciences and Engineering Research Council of Canada (NSERC) in the form of an Undergraduate Summer Research Award to Brent Cowan and a Discovery Grant  ... 
doi:10.1145/1496984.1497012 dblp:conf/fplay/CowanK08 fatcat:7nf5ptomljgwzc7f2yyhrqo3sq

Image-guided ToF depth upsampling: a survey

Iván Eichhardt, Dmitry Chetverikov, Zsolt Jankó
2017 Machine Vision and Applications  
This has motivated many researchers to combine ToF cameras with other sensors in order to enhance and upsample depth images.  ...  In this paper, we review the approaches that couple ToF depth images with high-resolution optical images. Other classes of upsampling methods are also briefly discussed.  ...  This research was supported in part by the program "Highly industrialised region on the west part of Hungary with limited R&D capacity: Research and development programs related to strengthening the strategic  ... 
doi:10.1007/s00138-017-0831-9 fatcat:w2p3ebhysfarfk46phex753dxe

Coupled geometric and texture PDE-based segmentation

A. Sofou, G. Evangelopoulos, P. Maragos
2005 IEEE International Conference on Image Processing 2005  
In this paper, along with recent trends in segmentation using multiple image cues, we examine the integration of modulation texture features, image contrast and region size for decomposition of an image  ...  Second, we analyze object surface texture by modelling image variations as local spatial modulation components estimated via multi-frequency filtering and instantaneous energy-tracking operators.  ...  In general, the methodology of marker extraction is application dependent and beyond the scope of this paper.  ... 
doi:10.1109/icip.2005.1530139 dblp:conf/icip/SofouEM05 fatcat:5kpc4p5cxrcanhjhh2aqedkho4

Filtering for texture classification: a comparative study

T. Randen, J.H. Husoy
1999 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we review most major filtering approaches to texture feature extraction and perform a comparative study.  ...  For reference, comparisons with two classical nonfiltering approaches, co-occurrence (statistical) and autoregressive (model based) features, are given.  ...  ACKNOWLEDGMENTS The authors would like to thank Kalle Karu and Jianchang Mao, both formerly at Michigan State University, for providing software for their approaches.  ... 
doi:10.1109/34.761261 fatcat:46emqau7lrg7fmoigro7yc77sq

Fields of Experts

Stefan Roth, Michael J. Black
2009 International Journal of Computer Vision  
While the model is trained on a generic image database and is not tuned toward a specific application, we obtain results that compete with specialized techniques.  ...  We demonstrate the capabilities of this Field-of-Experts model with two example applications, image denoising and image inpainting, which are implemented using a simple, approximate inference scheme.  ...  In making this comparison, it is important to keep in mind that Fields of Experts are generic image models with wide range of applications well beyond just image denoising.  ... 
doi:10.1007/s11263-008-0197-6 fatcat:xefw35ijtbew5huoek7w56chfa

Multiple hypotheses data association propagation for robust monocular-based SLAM algorithms

Mauricio Soto-Alvarez, Petri Honkamaa
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
Experimental results, using real and synthetic data, show that the proposed algorithm produces promising results with respect to other state of the art methods.  ...  Data Association is probably the most important step of every monocular Simultaneous Localization and Mapping (SLAM) algorithm because it provides the basic information to the estimation module, independently  ...  This algorithm does work very well in practice but it tends to be computationally expensive (beyond the real time usage).  ... 
doi:10.1109/icassp.2014.6854865 dblp:conf/icassp/AlvarezH14 fatcat:b2bjmsj46vglxl5c2abmr45e2q

Visual Object Target Tracking Using Particle Filter: A Survey

G.Mallikarjuna Rao, Ch. Satyanarayana
2013 International Journal of Image Graphics and Signal Processing  
This paper gives the survey of the existing developments of Visual object target tracking using particle filter from the last decade and discusses the advantage and disadvantages of various particle filters  ...  Image, Graphics and Signal Processing, 2013, 6, 57-71 Interacting Multiple Model Particle Filter: 3 Bayesian 3 Filtering : From Kalman Filters to Particle Filters , and Beyond VI Sequential Monte Carlo  ...  The algorithm is fast and is able to track a dynamic texture moving on another dynamic texture with different intrinsic dynamics.  ... 
doi:10.5815/ijigsp.2013.06.08 fatcat:olg4prc5pjghza3pwzi6cigvky

A Convolutional Neural Networks-Based Approach for Texture Directionality Detection

Marcin Kociołek, Michał Kozłowski, Antonio Cardone
2022 Sensors  
Subsequently, we defined and tested shallow and deep CNN architectures. We present the test results focusing on the CNN architectures and their robustness with respect to image perturbations.  ...  Here we test the applicability of convolutional neural networks (CNNs) to texture directionality detection.  ...  We would like to thank Anne L. Plant, John T. Elliot, and Kiran Bhadriraju from the Material Measurements Laboratory at NIST for sharing the fibroblast cell images that were used in this paper.  ... 
doi:10.3390/s22020562 pmid:35062522 pmcid:PMC8778371 fatcat:syx2owjqwneg5ppubm2dsj2qa4

Learning to Perceive Transparency from the Statistics of Natural Scenes

Anat Levin, Assaf Zomet, Yair Weiss
2002 Neural Information Processing Systems  
The optimization is performed using loopy belief propagation. We show that our model computes perceptually "correct" decompositions on synthetic images and discuss its application to real images.  ...  We present a probabilistic model of images based on the qualitative statistics of derivative filters and "corner detectors" in natural scenes and use this model to find the most probable decomposition  ...  Even for images with little texture standard belief propagation with synchronous updates did not converge. Significant manual tweaking was required to get BP to converge.  ... 
dblp:conf/nips/LevinZW02 fatcat:6palvhfgond4jbwb3jal352jcy
« Previous Showing results 1 — 15 out of 8,980 results