Filters








14,862 Hits in 4.8 sec

Coherent temporal extrapolation of labeled images

Gregoire Malandain, Gael Michelin
2017 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)  
In the present work, we propose an extrapolation method that coherently deformed the label images to be interpolated.  ...  In developmental imaging, 3D+t series of microscopic images allow to follow the organism development at the cell level and have now became the standard way of imaging the development of living organs.  ...  EXTRAPOLATION OF LABELED IMAGES Let consider now label images L 0 and L 1 that correspond to the segmented grey-level images I 0 and I 1 (see Fig. 1 ).  ... 
doi:10.1109/isbi.2017.7950554 dblp:conf/isbi/MalandainM17 fatcat:z6qrkgdwfbhktgl6gxl36ahjha

Slow and Steady Feature Analysis: Higher Order Temporal Coherence in Video

Dinesh Jayaraman, Kristen Grauman
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences.  ...  To this end, we train a convolutional neural network with a regularizer on tuples of sequential frames from unlabeled video.  ...  This work was supported in part by ONR YIP N00014-15-1-2291. used throughout our results, which let us leverage standard CNN architectures known to work well with tiny images [1] .  ... 
doi:10.1109/cvpr.2016.418 dblp:conf/cvpr/JayaramanG16 fatcat:l2wmapkndba4jngntgsghgu6bm

TemporalUV: Capturing Loose Clothing with Temporally Coherent UV Coordinates [article]

You Xie, Huiqi Mao, Angela Yao, Nils Thuerey
2022 arXiv   pre-print
We propose a novel approach to generate temporally coherent UV coordinates for loose clothing. Our method is not constrained by human body outlines and can capture loose garments and hair.  ...  Subsequently, a generative model is trained to balance the spatial quality and temporal stability. It is driven by supervised and unsupervised losses in both UV and image spaces.  ...  We show examples of the same region in the image to illustrate the temporal coherence of the generated videos.  ... 
arXiv:2204.03671v1 fatcat:t4gecf5xdngozg64afw7udb2da

Slow and steady feature analysis: higher order temporal coherence in video [article]

Dinesh Jayaraman, Kristen Grauman
2016 arXiv   pre-print
Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences.  ...  To this end, we train a convolutional neural network with a regularizer on tuples of sequential frames from unlabeled video.  ...  This work was supported in part by ONR YIP N00014-15-1-2291. used throughout our results, which let us leverage standard CNN architectures known to work well with tiny images [1] .  ... 
arXiv:1506.04714v2 fatcat:2mskrntojfcf3kyxdevggsykxm

Temporally Coherent General Dynamic Scene Reconstruction [article]

Armin Mustafa, Marco Volino, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
2020 arXiv   pre-print
and reconstruction to introduce temporal coherence; and a general robust approach for joint segmentation refinement and dense reconstruction of dynamic scenes by introducing shape constraint.  ...  This paper demonstrates unsupervised reconstruction of complete temporally coherent 4D scene models with improved non-rigid object segmentation and shape reconstruction and its application to free-viewpoint  ...  The scene is automatically decomposed into a set of spatio-temporally coherent objects as shown in Figure 1 where the resulting 4D scene reconstruction has temporally coherent labels and surface correspondence  ... 
arXiv:1907.08195v2 fatcat:pcjsowtlj5ejdpnidxerof2kcy

Space-Time Hole Filling With Random Walks in View Extrapolation for 3D Video

Sunghwan Choi, Bumsub Ham, Kwanghoon Sohn
2013 IEEE Transactions on Image Processing  
Index Terms-Depth image-based rendering, hole filling, inpainting, random walks, temporal coherence, view synthesis.  ...  The patch candidates that best describe the hole region are dynamically selected in the spacetime domain, and the hole is filled with the optimal patch for ensuring both spatial and temporal coherence.  ...  Index Terms-Depth image-based rendering, hole filling, inpainting, random walks, temporal coherence, view synthesis. I.  ... 
doi:10.1109/tip.2013.2251646 pmid:23481855 fatcat:zgiwjtoforhavfa5si65oswjce

Temporally Coherent General Dynamic Scene Reconstruction

Armin Mustafa, Marco Volino, Hansung Kim, Jean-Yves Guillemaut, Adrian Hilton
2020 International Journal of Computer Vision  
and reconstruction to introduce temporal coherence; and a general robust approach for joint segmentation refinement and dense reconstruction of dynamic scenes by introducing shape constraint.  ...  This paper demonstrates unsupervised reconstruction of complete temporally coherent 4D scene models with improved non-rigid object segmentation and shape reconstruction and its application to various applications  ...  To view a copy of this licence, visit http://creativecomm ons.org/licenses/by/4.0/.  ... 
doi:10.1007/s11263-020-01367-2 fatcat:k4a6n2l4hbfvdo6pp3gczrfhsq

Video stylization for digital ambient displays of home movies

Tinghuai Wang, John Collomosse, David Slatter, Phil Cheatle, Darryl Greig
2010 Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering - NPAR 10  
We present a novel algorithm based on multi-label graph cut for segmenting video into temporally coherent region maps.  ...  We demonstrate coherent segmentation and stylization over a variety of home videos.  ...  Acknowledgement This work was supported by HP Labs IRP funded studentship #474: "Artistic Rendering of Consumer Video".  ... 
doi:10.1145/1809939.1809955 dblp:conf/npar/WangCSCG10 fatcat:6vijt7q2ffhjnca6crnrin3q2i

Inpainting of Wide-baseline Multiple Viewpoint Video

Andrew Gilbert, Matt Trumble, Adrian Hilton, John Collomosse
2018 IEEE Transactions on Visualization and Computer Graphics  
the inpainting of large regions in a plausible manner conserving both spatial and temporal coherence.  ...  Uniquely, our algorithm addresses the domain of wide baseline multiple-viewpoint video (MVV) with no temporal look-ahead in near real time speed.  ...  The optimal inpainting of Ω h is the label map x minimizing the energy E(x) = D(x) + C(x), between D(x) the single vertex data potential, and C(x) the spatio-temporal coherence i.e pairwise potential.  ... 
doi:10.1109/tvcg.2018.2889297 pmid:30582545 fatcat:me4ewqi5krhhdbgy5mrn6wrlhi

Narrative speech production: An fMRI study using continuous arterial spin labeling

Vanessa Troiani, Maria A. Fernández-Seara, Ze Wang, John A. Detre, Sherry Ash, Murray Grossman
2008 NeuroImage  
Functional magnetic resonance imaging (fMRI) with continuous arterial spin labeling (CASL) was employed to monitor brain activation during narrative production of a semi-structured speech sample in healthy  ...  Significant activations were found in bilateral prefrontal and left temporal-parietal regions during narrative production relative to description of a single picture and relative to viewing the wordless  ...  Acknowledgment This work was supported in part by the National Institutes of Health (AG17586, NS44266, AG15116, NS53488).  ... 
doi:10.1016/j.neuroimage.2007.12.002 pmid:18201906 pmcid:PMC2291537 fatcat:fx25zgnq2fh4xa3lt5rx22zzfe

Change Detection Techniques with Synthetic Aperture Radar Images: Experiments with Random Forests and Sentinel-1 Observations

Pietro Mastro, Guido Masiello, Carmine Serio, Antonio Pepe
2022 Remote Sensing  
images.  ...  Then, we consider the additional pieces of information that can be recovered by comparing interferometric coherence maps related to couples of SAR images collected between a principal disastrous event  ...  The coherence between pairs of SAR images can be used as an indicator of the phase stability of the imaged scene over time, and tracking its temporal variations allows correlating it to the physical characteristics  ... 
doi:10.3390/rs14143323 fatcat:ihngruabkrdmrfo5vwnztcpioy

Mapping Canopy Height and Growing Stock Volume Using Airborne Lidar, ALOS PALSAR and Landsat ETM+

Oliver Cartus, Josef Kellndorfer, Markus Rombach, Wayne Walker
2012 Remote Sensing  
We show that the combined use of multi-temporal PALSAR intensity, coherence and Landsat yields higher retrieval accuracies than the retrieval with any of the datasets alone.  ...  A second set of randomForest models was developed using multi-temporal ALOS PALSAR intensities and repeat-pass coherences in two polarizations as well as Landsat data as predictor and stand-level ALS based  ...  Sergio Gonzales (Forestal Arauco) is acknowledged for the provision of the inventory data.  ... 
doi:10.3390/rs4113320 fatcat:pvp4hvrhqzdonpd67cgjogopyq

Laboratory observation of coherent structures beneath microscale and large-scale breaking waves under wind action

Sang-Ho Oh, Natsuki Mizutani, Kyung-Duck Suh
2008 Experimental Thermal and Fluid Science  
By analyzing PIV velocity data of wind-generated waves that are acquired at three different wind speeds, the similarity and difference in spatio-temporal evolving characteristics of the coherent structures  ...  In this study, it was shown that a single strong coherent structure, whose direction of rotation of the coherent structure was the same as the wave orbital motion, is formed immediately underneath large-scale  ...  Fig. 5 . 5 Spatio-temporal evolution of coherent structures generated by microscale breaking wave.  ... 
doi:10.1016/j.expthermflusci.2008.02.003 fatcat:czdma2fsrbbpfegogk3cvagaq4

Image-Guided Analysis of Shoulder Pathologies: Modelling the 3D Deformation of the Subacromial Space during Arm Flexion and Abduction [chapter]

Alexandra Branzan Albu, Denis Laurendeau, Luc. J. Hébert, Hélène Moffet, Marie Dufour, Christian Moisan
2004 Lecture Notes in Computer Science  
The 3D reconstruction technique is based on morphological morphing between adjacent slices and on contour-based extrapolation of extreme slices.  ...  The segmentation module integrates region and edge information in a coherent manner.  ...  interpolation and extrapolation (see Fig. 2 ).  ... 
doi:10.1007/978-3-540-25968-8_22 fatcat:h6ogtds6czb75l2xl3rxyjsn5y

Stylized ambient displays of digital media collections

Tinghuai Wang, John Collomosse, Rui Hu, David Slatter, Darryl Greig, Phil Cheatle
2011 Computers & graphics  
We present a novel algorithm based on multi-label graph cut for segmenting video into temporally coherent region maps.  ...  Our system is deployed on embedded hardware in the form of a compact digital photo frame. We demonstrate coherent segmentation and stylization over a variety of home videos and photos.  ...  temporally coherent regions.  ... 
doi:10.1016/j.cag.2010.11.004 fatcat:4rglznzsqfhjrhspdr6hqhgepq
« Previous Showing results 1 — 15 out of 14,862 results