Panoramaic Virtual tour publications
-
[Aliaga2006] Image Warping for Compressing and Spatially Organizing a Dense Collection of Images2006
Image-based rendering (IBR) systems create photorealistic views of complex 3D environments by resampling large collections of images captured in the environment. The quality of the resampled images increases significantly with image capture density. Thus, a significant challenge in interactive IBR systems is to provide both fast image access along arbitrary viewpoint paths and efficient storage of large image data sets. We describe a spatial image hierarchy combined with an image compression scheme that meets the requirements of interactive IBR walkthroughs. By using image warping and exploiting image coherence over the image capture plane, we achieve compression performance similar to traditional motion-compensated schema, e.g., MPEG, yet allow image access along arbitrary paths. Furthermore, by exploiting graphics hardware for image resampling, we can achieve interactive rates during IBR walkthroughs.
@article{Aliaga2006, author = {}, title = {Image Warping for Compressing and Spatially Organizing a Dense Collection of Images}, year = {2006}, crossref = {Max995,Adelson1991,Aliaga2001,McMillan1995,Aliaga2001,Aliaga2003b,Buehler2001,Gortler1996,Levoy1996,Shum1999,Wallace1991,ISO15444,Vetterli1995,Le1991,Popescu2006,Aliaga2005,Gersho1992,Ziv1977,Magnor2000,Peter2001,Gotz2002,Wilson2002b,Aliaga1999,Shade1998,Popescu1998,Mei2005,Yu2004,Popescu2000,Press1999,Nayar1997,Chang1999}, doi = {10.1016/j.image.2006.07.005}, file = {Aliaga2006.pdf:Aliaga2006.pdf:PDF}, keywords = {Image-based rendering, spatial hierarchy, compression, hierarchical, random access, image based, photographing, missing-refs, spatial video encoding}, owner = {tom}, timestamp = {2020-11-27} }
-
[Aliaga2005] A spatial image hierarchy for compression in image-based-rendering2005
Image-based rendering (IBR) systems create photorealistic views of complex 3D environments by resampling large collections of images captured in the environment. The quality of the resampled images increases significantly with higher image capture density. Thus, a significant challenge in interactive IBR systems is to provide both fast image access along arbitrary viewpoint paths and efficient storage of large image data sets. We describe a compression scheme based on a spatial image hierarchy that meets the requirements of interactive IBR walkthroughs. By exploiting image coherence over the entire image capture plane, we achieve compression performance similar to traditional motion-compensated schema, e.g., MPEG, yet allow image access along arbitrary paths. Furthermore, by exploiting graphics hardware for image resampling, we achieve interactive display rates during IBR walkthroughs.
@article{Aliaga2005, title = {A spatial image hierarchy for compression in image-based-rendering}, year = {2005}, crossref = {Aliaga2002,Aliaga2003a,Gortler1996,Gotz2002,Levoy1996,Magnor2000,Nayar1997,Peter2001,Wilson2002}, doi = {10.1109/ICIP.2005.1529824}, file = {Aliaga2005.pdf:Aliaga2005.pdf:PDF}, keywords = {Image-based rendering, spatial hierarchy, compression, hierarchical, random access, image based, photographing, patent, missing-refs, path-to-take, spatial video encoding}, owner = {tom}, timestamp = {2020-11-27} }
-
[Aliaga2003b] Sea of Images A Dense Sampling Approach for Rendering Large Indoor Environments2003
@article{Aliaga2003b, title = {Sea of Images A Dense Sampling Approach for Rendering Large Indoor Environments}, year = {2003}, crossref = {Debevec1998,Lippman1980}, file = {Aliaga2003b.pdf:Aliaga2003b.pdf:PDF}, keywords = {image-based rendering, capture, reconstruction, interactive, walkthrough, image based, missing-datasets, missing-refs, read, path-to-take, spatial video encoding}, owner = {tom}, timestamp = {2020-12-04} }
-
[Aliaga2002] Sea of Images2002
A long-standing research problem in computer graphics is to reproduce the visual experience of walking through a large photorealistic environment interactively. On one hand, traditional geometry-based rendering systems fall short of simulating the visual realism of a complex environment. On the other hand, image-based rendering systems have to date been unable to capture and store a sampled representation of a large environment with complex lighting and visibility effects. In this paper, we present a “Sea of Images,” a practical approach to dense sampling, storage, and reconstruction of the plenoptic function in large, complex indoor environments. We use a motorized cart to capture omnidirectional images every few inches on a eye-height plane throughout an environment. The captured images are compressed and stored in a multiresolution hierarchy suitable for real-time prefetching during an interactive walkthrough. Later, novel images are reconstructed for a simulated observer by resampling nearby captured images. Our system acquires 15,254 images over 1,050 square feet at an average image spacing of 1.5 inches. The average capture and processing time is 7 hours. We demonstrate realistic walkthroughs of real-world environments reproducing specular reflections and occlusion effects while rendering 15-25 frames per second.
@article{Aliaga2002, title = {Sea of Images}, year = {2002}, crossref = {Debevec1998,Lippman1980}, file = {Aliaga2002.pdf:Aliaga2002.pdf:PDF;Aliaga2002.video.avi.mp4:Aliaga2002.video.avi.mp4:MP4}, keywords = {image-based rendering, capture, reconstruction, interactive, walkthrough, image based, photographing, read, missing-datasets, missing-refs, path-to-take, spatial video encoding}, owner = {tom}, timestamp = {2020-11-27} }
-
[Aliaga2001] Plenoptic Stitching: A Scalable Method for Reconstructing 3D Interactive Walkthroughs2001
Interactive walkthrough applications require detailed 3D models to give users a sense of immersion in an environment. Traditionally these models are built using computer-aided design tools to define geometry and material properties. But creating detailed models is time-consuming and it is also difficult to reproduce all geometric and photometric subtleties of real-world scenes. Computer vision attempts to alleviate this problem by extracting geometry and photogrammetry from images of the realworld scenes. However, these models are still limited in the amount of detail they recover. Image-based rendering generates novel views by resampling a set of images of the environment without relying upon an explicit geometric model. Current such techniques limit the size and shape of the environment, and they do not lend themselves to walkthrough applications. In this paper, we define a parameterization of the 4D plenoptic function that is particularly suitable for interactive walkthroughs and define a method for its sampling and reconstructing. Our main contributions are: 1) a parameterization of the 4D plenoptic function that supports walkthrough applications in large, arbitrarily shaped environments; 2) a simple and fast capture process for complex environments; and 3) an automatic algorithm for reconstruction of the plenoptic function
@article{Aliaga2001, title = {Plenoptic Stitching: A Scalable Method for Reconstructing 3D Interactive Walkthroughs}, year = {2001}, crossref = {Adelson1991,Aliaga2001b,Chen1993,Chen1995,Debevec1996,Faugeras93,Faugeras98,Geyer98,Gortler96,Gottschalk96,Kang96, [Levoy96], [LeGall91], [Max95], [McMillan95], [Nalwa96],[Nayar97] [Rademacher98] [Roberts97] [Shi94] [Shum99] [Szeliski96] [Szeliski97] [Takahasi00], [Taylor00], [Tomasi91], [Wallace91], [Ward92], [Yu98], Ziv77}, doi = {10.1145/383259.383311}, file = {Aliaga2001.pdf:Aliaga2001.pdf:PDF;Aliaga2001.video.avi.mp4:Aliaga2001.video.avi.mp4:MP4}, keywords = {Image-based rendering, spatial hierarchy, compression, hierarchical, random access, image based missing-refs}, owner = {tom}, timestamp = {2020-11-28} }
-
[Wilson2002b] Spatially-Encoded Far-Field Representations for Interactive WalkthroughsWilson, Andrew, Mayer-Pate1, Ketan, and Manocha, Dinesh2002
We introduce the notion of spatially encoded video and use it for efficiently representing image-based impostors for interactive walkthroughs. As part of a pre-process, we automatically decompose the model and compute the far-fields. The resulting texture images are organized along multiple dimensions and can be accessed in a user-steered order at interactive rates. Our encoding algorithm can compress the impostors size by two orders of magnitude. Furthermore, the storage cost for additional impostors or samples grows sublinearly. The resulting system has been applied to a complex CAD environment composed of 13 million triangles. We are able to render it at interactive rates on a PC with little loss in image quality.
@article{Wilson2002b, author = {Wilson, Andrew and Mayer-Pate1, Ketan and Manocha, Dinesh}, title = {Spatially-Encoded Far-Field Representations for Interactive Walkthroughs}, year = {2002}, crossref = {Darsa1998}, file = {Wilson2002b.pdf:Wilson2002b.pdf:PDF}, keywords = {image databases, image-based rendering, MPEG, rendering systems, spatial data structures, read, missing-refs, video compression, path-to-take, video-codec, MPEG2}, owner = {tom}, timestamp = {2021-01-27}, url = {http://www.cs.unc.edu/ ̃geom/Video/SE} }
-
[Gotz2002] IRW: An Incremental Representation for Image-Based Walkthroughs2002
We present a new representation for image-based interactive walkthroughs. The target applications reconstruct a scene from novel viewpoints using samples from a spatial image dataset collected from a plane at eye-level. These datasets consist of pose augmented 2D images and often have a very large number of samples. Our representation exploits spatial coherence and rearranges the input samples as epipolar images. The base unit corresponds to a column of the original image that can be individually addressed and accessed. The overall representation, IRW, supports incremental updates, efficient encoding, scalable performance, and selective inclusion used by different reconstruction algorithms. We demonstrate the performance of our representation on a synthetic as well as a real-world environment.
@article{Gotz2002, title = {IRW: An Incremental Representation for Image-Based Walkthroughs}, year = {2002}, crossref = {}, file = {Gotz2002.pdf:Gotz2002.pdf:PDF}, keywords = {path-to-take,ray-space,read, missing-refs, image based, column-based, Cylindrical, panoramas }, owner = {tom}, timestamp = {2020-12-05}, url = {http://web.archive.org/web/20120516020127/http://www.cs.unc.edu/~gotz/projects/irw/} }
-
[Levoy1996] Light Field Rendering1996
A number of techniques have been proposed for flying through scenes by redisplaying previously rendered or digitized views. Techniques have also been proposed for interpolating between views by warping input images, using depth information or correspondences between multiple images. In this paper, we describe a simple and robust method for generating new views from arbitrary camera positions without depth information or feature matching, simply by combining and resampling the available images. The key to this technique lies in interpreting the input images as 2D slices of a 4D function - the light field. This function completely characterizes the flow of light through unobstructed space in a static scene with fixed illumination. We describe a sampled representation for light fields that allows for both efficient creation and display of inward and outward looking views. We hav e created light fields from large arrays of both rendered and digitized images. The latter are acquired using a video camera mounted on a computer-controlled gantry. Once a light field has been created, new views may be constructed in real time by extracting slices in appropriate directions. Since the success of the method depends on having a high sample rate, we describe a compression system that is able to compress the light fields we have generated by more than a factor of 100:1 with very little loss of fidelity. We also address the issues of antialiasing during creation, and resampling during slice extraction.
@article{Levoy1996, title = {Light Field Rendering}, year = {1996}, crossref = {}, doi = {10.1145/237170.237199}, file = {Levoy1996.pdf:Levoy1996.pdf:PDF}, keywords = {image-based rendering, light field, holographic stereogram, vector quantization, epipolar analysis, read, missing-refs, camera rig}, owner = {tom}, timestamp = {2020-12-05} }
-
[Lippman1980] Movie-maps: an application of the optical videodisc to computer graphicACM SIGGRAPH Computer Graphics Jul 1980
An interactive, dynamic map has been built using videodisc technology to engage the user in a simulated "drive" through an unfamiliar space. The driver, or map reader, is presented with either sparsely sampled sequences of images taken by single frame cameras that replicate actual imagery from a space, or with computer synthesized replicas of those images. The reader may control the speed, route,, angle of view and mode of presentation of this information and may thus tour the area. In addition, he may access spatially stored ancillary data stored in the buildings or in locales in the environment. This basic map is being enhanced to provide topographic views, and to incorporate optical and electronic image processing to provide a more responsive, visually complete representation of an environment.
@article{Lippman1980, title = {Movie-maps: an application of the optical videodisc to computer graphic}, journal = {ACM SIGGRAPH Computer Graphics}, year = {1980}, volume = {14}, pages = {32-42}, month = jul, doi = {10.1145/800250.807465}, file = {Lippman1980.pdf:Lippman1980.pdf:PDF}, isbn = {0-89791-021-4}, keywords = {optical videodisc; computer generated imagery; anamorphic imagery; image processing; interactive systems., image based, photographing, Image-based, Image-based rendering, missing-refs, read, path-to-take}, timestamp = {2020-12-04} }
-
[Matzen2014] Scene ChronologyIn Sep 2014
@inproceedings{Matzen2014, title = {Scene Chronology}, year = {2014}, month = sep, pages = {615-630}, doi = {10.1007/978-3-319-10584-0_40}, file = {Matzen2014.pdf:Matzen2014.pdf:PDF}, isbn = {978-3-319-10583-3}, keywords = {creation, photographing, image based, Image-based, Image-based rendering, to-read, missing-refs}, timestamp = {2019-11-14} }
-
[Aliaga2003a] Interactive Image-Based Rendering Using Feature Globalization2003
Image-based rendering (IBR) systems enable virtual walkthroughs of photorealistic environments by warping and combining reference images to novel viewpoints under interactive user control. A significant challenge in such systems is to automatically compute image correspondences that enable accurate image warping. In this paper, we describe a new algorithm for computing a globally consistent set of image feature correspondences across a wide range of viewpoints suitable for IBR walkthroughs. We first detect point features in a dense set of omnidirectional images captured on an eye-height plane. Then, we track these features from image to image, identifying potential correspondences when two features track to the same position in the same image. Among the potential correspondences, we select the maximal consistent set using a greedy graph-labeling algorithm. A key feature of our approach is that it exploits the multiple paths that can be followed between images in order to increase the number of feature correspondences between distant images. We demonstrate the benefits of this approach in a real-time IBR walkthrough system where novel images are reconstructed as the user moves interactively.
@article{Aliaga2003a, title = {Interactive Image-Based Rendering Using Feature Globalization}, year = {2003}, file = {Aliaga2003a.pdf:Aliaga2003a.pdf:PDF;Aliaga2003a.video.avi.mp4:Aliaga2003a.video.avi.mp4:MP4}, keywords = {Image-based rendering, reconstruction, interactive, correspondence, image features, photographing, read, missing-refs}, owner = {tom}, timestamp = {2020-11-29} }
-
[Grunheit2002] Efficient representation and interactive streaming of high-resolution panoramic viewsIn Proceedings. International Conference on Image Processing Sep 2002
A new system for interactive streaming of high-resolution 360/spl deg/ panoramic views over the Internet is presented. The scene is represented very efficiently using MPEG-4 BIFS and displayed at the client using the HHI 3-D MPEG-4 player. The user can navigate interactively through the scene. The navigation decisions are evaluated to trigger the streaming of the data needed to build the visible screen view and to ensure a fluent visualization of the scene. The system layout is designed to support other, more complex photo realistic 3-D environments later on and, thus, will enable the provision of a variety of new, interactive services over the Internet.
@inproceedings{Grunheit2002, title = {Efficient representation and interactive streaming of high-resolution panoramic views}, booktitle = {Proceedings. International Conference on Image Processing}, year = {2002}, volume = {3}, pages = {III-III}, month = sep, doi = {10.1109/ICIP.2002.1038942}, file = {Grunheit2002.pdf:Grunheit2002.pdf:PDF}, issn = {1522-4880}, keywords = {Internet;visual communication;client-server systems;interactive streaming;high-resolution panoramic views;Internet;MPEG-4 BIFS;client;HHI 3-D MPEG-4 player;fluent visualization;photo realistic 3-D environments;interactive services;Layout;Navigation;Rendering (computer graphics);Displays;MPEG 4 Standard;Data visualization;Virtual environment;Internet;Microcomputers;Computer graphics, missing-refs} }
-
[Zhang2003] A Survey on Image-Based Rendering - Representation, Sampling and CompressionJun 2003
Image-based rendering (IBR) has attracted a lot of research interest recently. In this paper, we survey the various techniques developed for IBR, including representation, sampling and compression. The goal is to provide an overview of research for IBR in a complete and systematic manner. We observe that essentially all the IBR representations are derived from the plenoptic function, which is seven dimensional and difficult to handle. We classify various IBR representations into two categories based on how the plenoptic function is simplified, namely restraining the viewing space and introducing source descriptions. In the former category, we summarize six common assumptions that were often made in various approaches and discuss how the dimension of the plenoptic function can be reduced based on these assumptions. In the latter category, we further categorize the methods based on what kind of source description was introduced, such as scene geometry, texture map or reflection model. Sampling and compression are also discussed respectively for both categories.
@techreport{Zhang2003, title = {A Survey on Image-Based Rendering - Representation, Sampling and Compression}, institution = {Carnegie Mellon University}, year = {2003}, type = {techreport}, number = {AMP 03-03}, month = jun, file = {Zhang2003.pdf:Zhang2003.pdf:PDF}, keywords = {read, compression} }
-
[Matthew2003] High-quality Image-based Interactive Exploration of Real-World EnvironmentsOct 2003
@techreport{Matthew2003, title = {High-quality Image-based Interactive Exploration of Real-World Environments}, institution = {Microsoft Corporation}, year = {2003}, type = {techreport}, number = {MSR-TR-2003-61}, month = oct, file = {MatthewUyttendaele2003.pdf:MatthewUyttendaele2003.pdf:PDF}, keywords = {mpeg-4, tiles, image based, read, missing-refs, camera rig} }
-
[Giesen2008a] Efficient Compression and Rendering in a Client-Server setting2008
@mastersthesis{Giesen2008a, title = {Efficient Compression and Rendering in a Client-Server setting}, year = {2008}, file = {Giesen2008a.pdf:Giesen2008a.pdf:PDF}, groups = {video}, keywords = {readed, missing-refs, server-side rending, geometry based, compression, video-codec} }
-
[Giesen2008b] Augmented Compression for Server-Side Rendering2008
@mastersthesis{Giesen2008b, title = {Augmented Compression for Server-Side Rendering}, year = {2008}, file = {Giesen2008b.pdf:Giesen2008b.pdf:PDF}, groups = {video}, keywords = {toread, missing-refs, server-side rending, geometry based, compression, video-codec} }
-
[Doellner2012] Server-Based Rendering of Large 3D Scenes for Mobile Devices Using G-Buffer Cube MapsIn
@inproceedings{Doellner2012, title = {Server-Based Rendering of Large 3D Scenes for Mobile Devices Using G-Buffer Cube Maps}, keywords = {read, Web-Based 3D Rendering, Service-Oriented 3D Rendering, Remote 3D Rendering, Large 3D Scene} }
-
[zhou2020] HoliCity: A City-Scale Data Platform for Learning Holistic 3D StructuresZhou, Yichao, Huang, Jingwei, Dai, Xili, Luo, Linjie, Chen, Zhili, and Ma, Yi2020
We present HoliCity, a city-scale 3D dataset with rich structural information. Currently, this dataset has 6,300 real-world panoramas of resolution 13312 × 6656 that are accurately aligned with the CAD model of downtown London with an area of more than 20 km 2 , in which the median re- projection error of the alignment of an average image is less than half a degree. This dataset aims to be an all-in-one data platform for research of learning abstracted high-level holis- tic 3D structures that can be derived from city CAD models, e.g., corners, lines, wireframes, planes, and cuboids, with the ultimate goal of supporting real-world applications in- cluding city-scale reconstruction, localization, mapping and augmented reality. The accurate alignment of the 3D CAD models and panoramas also benefits low-level 3D vision tasks such as surface normal estimation, as the surface nor- mal extracted from previous LiDAR-based datasets is often noisy. We conduct experiments to demonstrate the applica- tions of HoliCity, such as predicting surface segmentation, normal maps, depth maps, and vanishing points, as well as test the generalizability of methods trained on HoliCity and other related datasets.
@article{zhou2020, author = {Zhou, Yichao and Huang, Jingwei and Dai, Xili and Luo, Linjie and Chen, Zhili and Ma, Yi}, title = {{HoliCity}: A City-Scale Data Platform for Learning Holistic {3D} Structures}, year = {2020}, note = {arXiv:2008.03286 [cs.CV]}, archiveprefix = {arXiv}, groups = {dataset}, keywords = {to-read, dataset}, url = {http://holicity.io} }
-
[xiaz2018] Gibson Env: real-world perception for embodied agentsXia, Fei, R. Zamir, Amir, He, Zhi-Yang, Sax, Alexander, Malik, Jitendra, and Savarese, SilvioIn Computer Vision and Pattern Recognition (CVPR), 2018 IEEE Conference on 2018
@inproceedings{xiaz2018, author = {Xia, Fei and R. Zamir, Amir and He, Zhi-Yang and Sax, Alexander and Malik, Jitendra and Savarese, Silvio}, title = {Gibson {Env}: real-world perception for embodied agents}, booktitle = {Computer Vision and Pattern Recognition (CVPR), 2018 IEEE Conference on}, year = {2018}, organization = {IEEE} }
-
[Wilson2002c] Spatially Encoded Image-Space Simplifications for Interactive WalkthroughWilson, Andrew2002
@mastersthesis{Wilson2002c, author = {Wilson, Andrew}, title = {Spatially Encoded Image-Space Simplifications for Interactive Walkthrough}, year = {2002}, file = {:/home/tom/github/website/Articles.tomasparks.name/trunk/vt/wilson2002c.pdf:PDF}, keywords = {path-to-take, read, video-codec, MPEG2, spatial video encoding} }
-
[Rsch2017] Efficient Compression for Server-side G-buffer Streaming in Web ApplicationsR\asch, Sascha, Herz, Maximilian, Behr, Johannes, and Kuijper, ArjanIn Proceedings of the 22Nd International Conference on 3D Web Technology 2017
@inproceedings{Rsch2017, author = {R\asch, Sascha and Herz, Maximilian and Behr, Johannes and Kuijper, Arjan}, title = {Efficient Compression for Server-side G-buffer Streaming in Web Applications}, booktitle = {Proceedings of the 22Nd International Conference on 3D Web Technology}, year = {2017}, series = {Web3D '17}, pages = {16:1-16:7}, address = {New York, NY, USA}, publisher = {ACM}, doi = {10.1145/3055624.3075952}, file = {Rsch2017.pdf:Rsch2017.pdf:PDF}, groups = {crossRefs}, isbn = {978-1-4503-4955-0}, keywords = {web3D}, location = {Brisbane, Queensland, Australia}, url = {http://doi.acm.org/10.1145/3055624.3075952} }