Filters








10,415 Hits in 6.4 sec

Computational zoom

Abhishek Badki, Orazio Gallo, Jan Kautz, Pradeep Sen
2017 ACM Transactions on Graphics  
ACKNOWLEDGMENTS We thank Arjun Muralidharan, Chitra Karanam, Desire Luong, Ekta Prashnani, Nihar Talele, Qiaodong Cui, Robert Maier, and Saandeep Depatla for helping with the datasets.  ...  THE COMPUTATIONAL ZOOM FRAMEWORK The goal of our computational zoom framework is post-capture modi cation of a picture's composition.  ...  CONCLUSION In this paper, we have presented computational zoom, a framework that enables photographers to adjust the composition of an image post capture.  ... 
doi:10.1145/3072959.3073687 fatcat:74c7xx5izjeoxixbftdvqbd4za

The Stereoscopic Zoom

Sergi Pujades, Frederic Devernay, Laurent Boiron, Remi Ronfard
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
However, we show that two cameras are unable to create compelling stereoscopic images for extreme focal length lenses.  ...  We study camera models to generate stereoscopic zoom shots, i.e. using very long focal length lenses. Stereoscopic images are usually generated with two cameras.  ...  Note that this computation is only valid for a flat element at a single depth.  ... 
doi:10.1109/cvprw.2017.170 dblp:conf/cvpr/PujadesDBR17 fatcat:jztotebvvzdffl7x4ooeq62gqq

Image Zoom Completion

Moncef Hidane, Mireille El Gheche, Jean-Francois Aujol, Yannick Berthoumieu, Charles-Alban Deledalle
2016 IEEE Transactions on Image Processing  
We refer to this task as the image zoom completion problem.  ...  We consider the problem of recovering a highresolution image from a pair consisting of a complete lowresolution image and a high-resolution but incomplete one.  ...  THE IMAGE ZOOM COMPLETION PROBLEM The setting for IZC is a complete LR image and a corresponding incomplete HR image.  ... 
doi:10.1109/tip.2016.2571061 pmid:27249829 fatcat:zuvtbtdbhfaqlijz4yyc7p5awe

Zooming On All Actors: Automatic Focus+Context Split Screen Video Generation

Moneish Kumar, Vineet Gandhi, Remi Ronfard, Michael Gleicher
2017 Computer graphics forum (Print)  
crop-and zoom.  ...  Recordings of stage performances are easy to capture with a high-resolution camera, but are difficult to watch because the actors' faces are too small.  ...  Special thanks to Claudia Stavisky, Auxane Dutronc and the cast and crew of 'Death of a Salesman' and 'Cat on a hot tin roof'.  ... 
doi:10.1111/cgf.13140 fatcat:y63aesvoirhuvfewzlmtvzpzxa

Video tapestries with continuous temporal zoom

Connelly Barnes, Dan B. Goldman, Eli Shechtman, Adam Finkelstein
2010 ACM Transactions on Graphics  
Figure 1 : A multiscale tapestry represents an input video as a seamless and zoomable summary image which can be used to navigate through the video.  ...  See the video to view the continuous zoom animation between the scales. For Copyright reasons, the print and electronic versions of this paper contain different imagery in Figures 1, 4 , 6, and 7.  ...  Acknowledgements We thank Lorelay Bove for the color script.  ... 
doi:10.1145/1833351.1778826 fatcat:s45fjge3pbf6bkblrji2c2z4dy

Video tapestries with continuous temporal zoom

Connelly Barnes, Dan B. Goldman, Eli Shechtman, Adam Finkelstein
2010 ACM SIGGRAPH 2010 papers on - SIGGRAPH '10  
discrete moments in time, and a user can zoom smoothly into the image to reveal additional temporal details.  ...  Abstract We present a novel approach for summarizing video in the form of a multiscale image that is continuous in both the spatial domain and across the scale dimension: There are no hard borders between  ...  Acknowledgements We thank Lorelay Bove for the color script. The short film Kind of a Blur is c Skunk Creek Productions.  ... 
doi:10.1145/1833349.1778826 fatcat:4ydff3i72vccxgfrc73dncatsm

Video tapestries with continuous temporal zoom

Connelly Barnes, Dan B. Goldman, Eli Shechtman, Adam Finkelstein
2010 ACM Transactions on Graphics  
discrete moments in time, and a user can zoom smoothly into the image to reveal additional temporal details.  ...  Abstract We present a novel approach for summarizing video in the form of a multiscale image that is continuous in both the spatial domain and across the scale dimension: There are no hard borders between  ...  Acknowledgements We thank Lorelay Bove for the color script. The short film Kind of a Blur is c Skunk Creek Productions.  ... 
doi:10.1145/1778765.1778826 fatcat:e4ycakw7i5a5xfymad45inpi4i

sZoom: A Framework for Automatic Zoom into High Resolution Surveillance Videos [article]

Mukesh Saini and Benjamin Guthier and Hao Kuang and Dwarikanath Mahapatra and Abdulmotaleb El Saddik
2019 arXiv   pre-print
In this paper, we propose sZoom, a framework to automatically zoom into a high resolution surveillance video.  ...  The proposed framework selectively zooms into the sensitive regions of the video to present details of the scene, while still preserving the overall context required for situation assessment.  ...  In this paper, we propose sZoom, a novel automatic zoom framework for surveillance videos. This is shown in Figure 1 .  ... 
arXiv:1909.10164v1 fatcat:oyg576sj2rcarbgts64t5xxvda

Dust evolution in zoom-in cosmological simulations of galaxy formation [article]

Gian Luigi Granato, Cinthia Ragone-Figueroa, Antonela Taverna, Laura Silva, Milena Valentini, Stefano Borgani, Pierluigi Monaco, Giuseppe Murante, Luca Tornatore
2021 arXiv   pre-print
We present cosmological zoom-in hydro-dynamical simulations for the formation of disc galaxies, implementing dust evolution and dust promoted cooling of hot gas.  ...  for three disc galaxies of different masses.  ...  ACKNOWLEDGEMENTS We warmly thank Mónica Relaño for helping us in comparing our model with the results of her group, and Peter Camps for advice in using the radiative transfer code SKIRT.  ... 
arXiv:2010.05919v2 fatcat:hnnlynw6mjgmxhd7guju5ziqp4

Zooming In on Choice: How Do Consumers Search for Cameras Online?

Bart J. Bronnenberg, Jun B. Kim, Carl F. Mela
2016 Marketing science (Providence, R.I.)  
W e describe online consumers' search behavior for differentiated durable goods using a data set that captures a detailed level of consumer search and attribute information for digital cameras.  ...  We discuss these and other findings in the context of optimal search strategies and discuss the prospects for consumer learning during search.  ...  Therefore, for any given consumer, ordering on V promotes ordering of attribute tuples in a linear utility framework.  ... 
doi:10.1287/mksc.2016.0977 fatcat:z4mlx3asbbc4foev4ffjm2fcva

Simultaneous varifocal and broadband achromatic computational imaging using quartic metasurfaces [article]

Shane Colburn, Arka Majumdar
2019 arXiv   pre-print
By engineering a near spectrally invariant point spread function, we image full-color patterns under white light over a 5x zoom range.  ...  Comprising two quartic phase metasurfaces and a post-capture deconvolution algorithm, the system exhibits an extended depth of focus with an adjustable focal length range of 4.8 mm (a 667-diopter change  ...  Acknowledgements: Part of this work was conducted at the Washington Nanofabrication Facility / Molecular Analysis Facility, a National Nanotechnology Coordinated Infrastructure (NNCI) site at the University  ... 
arXiv:1904.09622v1 fatcat:asyqd3k4nfbc5gdyimqlizdgrm

Computational stereo camera system with programmable control loop

Simon Heinzle, Pierre Greisen, David Gallup, Christine Chen, Daniel Saner, Aljoscha Smolic, Andreas Burg, Wojciech Matusik, Markus Gross
2011 ACM Transactions on Graphics  
In this paper, we present a computational stereo camera system that closes the control loop from capture and analysis to automatic adjustment of physical parameters.  ...  Computational power and flexibility is enabled by a dedicated software and hardware architecture. We show that even traditionally difficult shots can be easily captured using our system.  ...  Post-production. Some systems allow changing depth composition of S3D content after capture. Kawai et al. [2002] present an editing system that allows basic alignment and checks.  ... 
doi:10.1145/2010324.1964989 fatcat:kn5mp4lcprdcfknqnhoyonhjim

A Graph Neural Network-Based Map Tiles Extraction Method Considering POIs Priority Visualization on Web Map Zoom Dimension

Huaze Xie, Da Li, Yuanyuan Wang, Yukiko Kawai
2022 IEEE Access  
for each map tile zoom dimension.  ...  The predictive performance of the proposed method is more than 56% for each zoom level on 60 randomly-selected map tiles in Kyoto City.  ...  This is the first time that map zoom level has been applied as a map dimension to a graph structure framework.  ... 
doi:10.1109/access.2022.3182497 fatcat:kf4stsyshvhsxjr2hnjoohoulu

3DB: A Framework for Debugging Computer Vision Models [article]

Guillaume Leclerc, Hadi Salman, Andrew Ilyas, Sai Vemprala, Logan Engstrom, Vibhav Vineet, Kai Xiao, Pengchuan Zhang, Shibani Santurkar, Greg Yang, Ashish Kapoor, Aleksander Madry
2021 arXiv   pre-print
We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation.  ...  We demonstrate, through a wide range of use cases, that 3DB allows users to discover vulnerabilities in computer vision systems and gain insights into how models make decisions. 3DB captures and generalizes  ...  E.7 Performance scaling (Appendix A) The only relevant details for this experiment are the fact that we ran 10 policies (at most 5 concurrently).  ... 
arXiv:2106.03805v1 fatcat:mb47eur7h5ddjiiypnl5jnpkdi

Zooming in on Individual Star Formation: Low- and High-mass Stars [article]

Anna L. Rosen, Stella S.R. Offner, Sarah I. Sadavoy, Asmita Bhandare, Enrique Vázquez-Semadeni, Adam Ginsburg
2020 arXiv   pre-print
During the last decade a variety of technological and computing advances have transformed our understanding of star formation through the use of multi-wavelength observations, large scale observational  ...  Several physical processes like turbulence, magnetic fields and stellar feedback, such as radiation pressure and outflows, are more or less important for different stellar masses and size scales.  ...  temperature and µ is the mean molecular weight typically taken to be 2.33 for molecular gas at solar composition.  ... 
arXiv:2005.07717v1 fatcat:4ee5sdpeqrfa5hdebnzht2ldnm
« Previous Showing results 1 — 15 out of 10,415 results