Filters








5,767 Hits in 4.5 sec

Compressive Light Field Reconstructions Using Deep Learning

Mayank Gupta, Arjun Jauhari, Kuldeep Kulkarni, Suren Jayasuriya, Alyosha Molnar, Pavan Turaga
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
The combination of compressive light field capture with deep learning allows the potential for real-time light field video acquisition systems in the future.  ...  We present a deep learning approach using a new, two branch network architecture, consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution 4D light field from a single coded 2D image  ...  KK and PT were partially supported by NSF CAREER grant 1451263. SJ was supported by a NSF Graduate Research Fellowship and a Qualcomm Innovation Fellowship.  ... 
doi:10.1109/cvprw.2017.168 dblp:conf/cvpr/GuptaJKJMT17 fatcat:atffoqvybjgc3dnso5qh5djwoy

Compressive Light Field Reconstructions using Deep Learning [article]

Mayank Gupta, Arjun Jauhari, Kuldeep Kulkarni, Suren Jayasuriya, Alyosha Molnar, Pavan Turaga
2018 arXiv   pre-print
The combination of compressive light field capture with deep learning allows the potential for real-time light field video acquisition systems in the future.  ...  We present a deep learning approach using a new, two branch network architecture, consisting jointly of an autoencoder and a 4D CNN, to recover a high resolution 4D light field from a single coded 2D image  ...  KK and PT were partially supported by NSF CAREER grant 1451263. SJ was supported by a NSF Graduate Research Fellowship and a Qualcomm Innovation Fellowship.  ... 
arXiv:1802.01722v1 fatcat:h4calra7hbd6vpqvs7yczbuhhm

On object-based compression for a class of dynamic image-based representations

Qing Wu, King-To Ng, Shing-Chow Chan, Heung-Yeung Shum
2005 IEEE International Conference on Image Processing 2005  
Experimental results show that considerable improvements in coding performance are obtained for both synthetic and real scenes.  ...  The proposed compression scheme exploits both the temporal and spatial redundancy among video object streams in the PV to achieve higher compression efficiency.  ...  In addition, the random access to individual pixels in the compressed data stream, so-called the random access problem in IBR, becomes very important in real-time rendering.  ... 
doi:10.1109/icip.2005.1530414 dblp:conf/icip/WuNCS05 fatcat:4v7erbprifgjbn4ytlseuhxzwe

4D video textures for interactive character appearance

Dan Casas, Marco Volino, John Collomosse, Adrian Hilton
2014 Computer graphics forum (Print)  
performance capture reconstructs dynamic shape and appearance over time but is limited to free-viewpoint video replay of the same motion.  ...  4D Video Textures (4DVT) introduce a novel representation for rendering video-realistic interactive character animation from a database of 4D actor performance captured in a multiple camera studio. 4D  ...  We thank Margara Tejera for helping during the capture of dataset Dan, Peng Huang for extracting background camera features for Fig 1, and RE@CT partners for their help in acquiring datasets Infantry  ... 
doi:10.1111/cgf.12296 fatcat:uatwd3xkrzgg7kxmlx5ust46qm

RLFC

Srihari Pratapa, Dinesh Manocha
2019 Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games - I3D '19  
The decompression times for decoding the blocks of LFI are 1 - 3 microseconds per channel on an NVIDIA GTX-960 and we can render new views with a resolution of 512X512 at 200 fps.  ...  Furthermore, we use bounded integer sequence encoding which provides random access and fast hardware decoding for compressing the blocks of children of the tree.  ...  Levoy and Hanrahan [1996] use this observation to present a simple twoplane (4D) parametrization of the plenoptic function and describe a practical light field rendering scheme for real-time photo-realistic  ... 
doi:10.1145/3306131.3317018 dblp:conf/si3d/PratapaM19 fatcat:uqr2vvuiaze5xpf4roqvwq2qce

Out-of-core compression and decompression of large n-dimensional scalar fields

Lawrence Ibarria, Peter Lindstrom, Jarek Rossignac, Andrzej Szymczak
2003 Computer graphics forum (Print)  
The proposed approach may be used both for lossy and lossless compression and is well suited for out-of-core compression and decompression, because a trivial implementation, which sweeps through the data  ...  We present a simple method for compressing very large and regularly sampled scalar fields.  ...  Because of the limited size of its footprint, the predictor is well suited for out-of-core streaming compression and decompression.  ... 
doi:10.1111/1467-8659.00681 fatcat:ff5xo6cyq5fjfoynmuw5gaerui

A model for adapting 3D graphics based on scalable coding, real-time simplification and remote rendering

Marius Preda, Paulo Villegas, Franciso Morán, Gauthier Lafruit, Robert-Paul Berretty
2008 The Visual Computer  
Scalability at the level of content, platforms and networks is exploited to achieve the best trade-offs between complexity and quality.  ...  Most current multiplayer 3D games can only be played on dedicated platforms, requiring specifically designed content and communication over a predefined network.  ...  BIFS defines a binary encoded version of an extended set of VRML, trying to balance the compression performances with the extensibility, ease of parsing and simple bit-stream syntax.  ... 
doi:10.1007/s00371-008-0284-2 fatcat:mtmgbx65abfthofs636jimj75q

Real-time interactive 4D-STEM phase-contrast imaging from electron event representation data [article]

Philipp M. Pelz, Ian Johnson, Colin Ophus, Peter Ercius, Mary C. Scott
2021 arXiv   pre-print
We detail the computational complexity advantages of the EER and the necessary computational steps to achieve real-time interactive ptychography and center-of-mass differential phase contrast using commonly  ...  Here we show with experimental data from the 4D Camera that linear-index encoded EER and its direct use in 4D-STEM phase contrast imaging methods enables real-time, interactive phase-contrast from large-area  ...  Minor, James Ciston, and John Joseph who contributed to the development of the 4D Camera. We thank Scott Stonemeyer for providing the multi-wall carbon nanotube samples.  ... 
arXiv:2104.06336v1 fatcat:4onnjrdipvbm5bcyen5fibc5ke

A multi-stream adaptation framework for bandwidth management in 3D tele-immersion

Zhenyu Yang, Bin Yu, Klara Nahrstedt, Ruzena Bajscy
2006 Proceedings of the 2006 international workshop on Network and operating systems support for digital audio and video - NOSSDAV '06  
However, along with the promise a new set of challenges have emerged including the real-time acquisition, streaming and rendering of 3D scenes to convey a realistic sense of immersive spaces.  ...  We implement a prototype of the framework that integrates semantic stream selection, content adaptation, and 3D data compression services with user preference.  ...  The presented views are those of authors and do not represent the position of NSF. We would also like to thank Sang-hack Jung for providing us the teleimmersive videos.  ... 
doi:10.1145/1378191.1378209 dblp:conf/nossdav/YangYNB06 fatcat:yryvdznt3bgdhaapgtjqixri4m

An object-based compression system for a class of dynamic image-based representations

Qing Wu, King-To Ng, Shing-Chow Chan, Heung-Yeung Shum
2005 Visual Communications and Image Processing 2005  
To improve the coding performance, the proposed compression system exploits both the temporal redundancy and spatial redundancy among the video object streams in the PV by employing disparitycompensated  ...  for both synthetic scene and real scene, while supporting the stated object-based functionalities.  ...  Furthermore, the random access to individual pixels inside the compressed data stream, so-called the random access problem in IBR, becomes a very important issue in real-time rendering.  ... 
doi:10.1117/12.632666 fatcat:inh3ch3wxje5ffttw7ktbds3t4

Improved methods for object-based coding of plenoptic videos

Qing Wu, Shing-Chow Chan, Heung-Yeung Shum
2005 2005 International Symposium on Intelligent Signal Processing and Communication Systems  
Experimental results show that considerable improvements in texture coding performance are obtained for both synthetic and real scenes. The improved depth coding quality is also illustrated.  ...  Upon this object-based coding framework, the paper studies the improved coding methods for the texture and depth coding to achieve better compression efficiency.  ...  In addition, the random access to individual pixels in the compressed data stream, so-called the random access problem in IBR, becomes very important in real-time rendering.  ... 
doi:10.1109/ispacs.2005.1595451 fatcat:qt4psguf5bc6disnhvrh55t37q

Efficient 4D motion compensated lossless compression of dynamic volumetric medical image data

V. Sanchez, P. Nasiopoulos, R. Abugharbieh
2008 Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing  
Performance evaluations on real medical images of varying modality resulted in lossless compression ratios of up to 16:1.  ...  Dynamic volumetric (four dimensional-4D) medical images are typically huge in file size and require a vast amount of resources for storage and transmission purposes.  ...  RESULTS AND DISCUSSION We tested our proposed compression method on real 4D medical images consisting of six fMRI, two 4D-MRI and two PET sequences.  ... 
doi:10.1109/icassp.2008.4517668 dblp:conf/icassp/SanchezNA08 fatcat:era3nogqnfhqfepq6my35t6upi

3D RGB image compression for interactive applications

Chandrajit Bajaj, Insung Ihm, Sanghun Park
2001 ACM Transactions on Graphics  
Our compression technique is suitable for applications wherein data are accessed in a somewhat unpredictable fashion, and real-time performance of decompression is necessary.  ...  This paper presents a new 3D RGB image compression scheme designed for interactive real-time applications.  ...  We also wish to thank Viewpoint, the Stanford University Computer Graphics Lab, the RenderMan software [Upstill 1990 ], and the Blue Moon Rendering Tools (BMRT) for their public polygonal models and surface  ... 
doi:10.1145/383745.383747 fatcat:yq2n3wchj5fbvdq74xnyha4wra

WebGL-based Streaming and Presentation Framework for Bidirectional Texture Functions [article]

Christopher Schwartz, Roland Ruiters, Michael Weinmann, Reinhard Klein
2011 VAST: International Symposium on Virtual Reality  
Our approach works out-of-the-box in modern web browsers and allows for the progressive transmission and interactive rendering of digitized artifacts consisting of 3D geometry and reflectance information  ...  We handle the huge amount of data needed for this representation by employing a novel progressive streaming approach for BTFs which allows for the smooth interactive inspection of a steadily improving  ...  We would like to thank Raoul Wessel for proposing the idea and Nils Jenniche for helping with the implementation.  ... 
doi:10.2312/vast/vast11/113-120 fatcat:xv2wpbg4svdddnfrvqql4xylqu

HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media

Anargyros Chatzitofis, Leonidas Saroglou, Prodromos Boutis, Petros Drakoulis, Nikolaos Zioulis, Shishir Subramanyam, Bart Kevelham, Caecilia Charbonnier, Pablo Cesar, Dimitrios Zarpalas, Stefanos Kollias, Petros Daras
2020 IEEE Access  
By capturing 2 female and 2 male professional actors performing various full-body movements and expressions, HUMAN4D provides a diverse set of motions and poses encountered as part of single- and multi-person  ...  We provide evaluation baselines by benchmarking HUMAN4D with state-of-the-art human pose estimation and 3D compression methods.  ...  VOLUMETRIC VIDEO COMPRESSION Compression of volumetric data produced in a real-time manner is thought to be a key enabler of a wide variety of applications, such as XR teleconference, real-time dense surface  ... 
doi:10.1109/access.2020.3026276 fatcat:tz2c32q2djfb3jne6ore7spiay
« Previous Showing results 1 — 15 out of 5,767 results