4 days ago - Just because they're an independent publisher, or new to the game and was told “this is. I, Jane Reader, certainly did not know all this went on. Nora, you had me at Whiskey Tango Foxtrot. What a load of manure! The resources they should to catching it and getting rid of people like RR Banks. Apr 26, 2018 - The families who turned out for an April 25 screening of Sony's “Peter Rabbit” at Event Cinemas in Innaloo, Western Australia got a terrifying. Android Apps APK - Find the best apps, games & download for free! Best Free Android Wallpapers. Snowflake Macro Orange Background in Nature 1080x1920. UC Browser - Fast Download Private & Secure. UC Browser is a free web browser for android. Download APK. Pokemon GO Tips: 10 Frustrating Problems and Fixes – Unable to Download, Already Own This Item, Authentication Issues, and More. Download apk for Android with APKPure APK downloader. NoAds, Faster apk downloads and apk file update speed. Best of all, it's free.
|
In recent years, the number of range scanners and surface reconstructionalgorithms has been growing rapidly. Many researchers, however, do not haveaccess to scanning facilities or dense polygonal models. The purpose of thisrepository is to make some range data and detailed reconstructions available tothe public. Here's how the models in this repository were created:
Scanning and surface reconstruction
The first set of models below, called 'The Stanford Models', were scanned witha Cyberware 3030 MS scanner, with theexception of Lucy, who was scanned with theStanford Large Statue Scanner, designed for theDigital Michelangelo Project.Both scanners are swept-stripe, laser triangulation range scanners. Thetriangulation calculations all the Stanford models except the Happy Buddha andDragon were performed in hardware by the Cyberware scanner(s). These last twomodels were acquired using Brian Curless's spacetimeanalysis. Each scan takes the form of a range image, described in thelocal coordinate system of the scanner. To merge these range images, we mustfirst align them together. For all the Stanford models,alignment was done using a modified ICP algorithm, as described inthis paper.These alignments are stored in '.conf' files, which list each range image inthe model along with a translation and a quaternion rotation. Finally, thealigned range images are combined to produce a single triangle mesh (a processsometimes called surface reconstruction) using eitherzippering or volumetric merging,two methods developed at Stanford. The entry for each model indicates whichmethod was used. Implementations of both methods are currently available fordownload, respectively, atZipPack andVripPack.The second method is the surface reconstruction method invoked by theScanalyze software package used in theDigital Michelangelo Project.Another software package that might be of interest isVolfill, our diffusion-based hole filler forlarge polygon meshes.
The second set of models below were acquired at a XY scan resolution of 100microns using theXYZ RGB auto-synchronized camera, which isbased on technology developed in theVisual Information Technology group of the Canadian National ResearchCouncil (NRC). This camera has an accuracy (3 Sigma) of ± 0.025mm(±0.001'), and X, Y, and Z-axis resolutions of 0.1mm (0.004'),0.002mm (0.00008'), and 0.003mm (0.0001'), respectively, asdetermined using a DEA Scirocco coordinate measuring machine. Allpost-processing, including alignment, merging, editing, and polygon reduction,were done usingInnovmetric's Polyworks software.These models come to us courtesy of Helmut Kungl.
File format
Unless otherwise noted, the range data and reconstructed models in thisrepository are stored in PLY files. This format was developed at StanfordUniversity, and the source code is available fordownload. For convenience, we have represented most of these PLY files intheir ASCII formats. Choosing ASCII makes it possible for someoneunfamiliar with it to get a feel for the file format, and it avoidsthe problem of using the correct big-endian vs. little-endian byteorders.To view PLY files, you can download ourScanalyze software package.For converting PLY files to other formats,here are some converters we have or know about:
- Our utility for converting PLY filesto Inventor files. Click here to download the executable.
- Richard Harding of the Sony Playstation group has contributed aply-to-Maya plugin.It supports import from PLY to Maya, and export from Maya to PLY,for versions 6.0 and 7.0 of Maya.Starting with Maya 8.5, this exporter can be downloaded fromhttp://sites.google.com/site/mayaplyimportexport/.
- Bruce Merry of South Africa haswritten a script to import PLY files to Blender. Clickhere to download it.
- A shareware program written by ZoltanKarpati for converting between many 3D formats, including PLY.
- For converting PLY to OBJ/3DS formats, there used to be a free demo version ofDeep Exploration, available here,but we hear it is no longer available.
- Diego Nehab (Princeton) has also written atoolkit for manipulating PLY files.
- Another site with information about PLY files is thePLY File Format page ofthe Georgia Institute of Technology'sLarge Geometric Models Archive.
- João Oliveira of University College London has modified the Georgia Techlibraries so that reading of PLY files is robust to the line breaksinserted when editing them on various platforms.Here is his package.
- Okino's PolyTrans package includes a PLYimporter andexporter.
- Paolo Cignoni's MeshLab system, available fromSourceForge.
- A C++ library for parsing PLY files, written by Ares Lagae,is available here.
Range data versus 3D models - a caveat on the use of these models
The models in this archive are fairly widely used in the graphics,visualization, and vision communities. Things people have done with thesemodels include simplification, multi-resolution representation, curved surfacefitting, compression, texture mapping, modeling, deformation, animation,physically-based simulation, texture synthesis, and rendering. The StanfordBunny is particularly widely used, as surveyed by Greg Turk on thisentertainingweb page.
One use people have made of these models is as input for surface reconstructionalgorithms, typically by stripping away the mesh connectivity and treating thevertices as an unorganized point cloud. We caution against this approach. Ourzippering andvolumetric range image merging methods produce smooth, (usually) manifoldsurfaces. More specifically, they eliminate outliers in the range data, reducenoise, mask misalignments between range images, and generally hide many of theerrors that arise naturally during 3D scanning. In this sense, ourreconstructed models do not constitute realistic input data for a surfacereconstruction algorithm.
If you want to experiment with a new reconstruction algorithm, and especiallyif you want to compare its performance against existing methods, then youshould start with real range data. For many of the models in this archive,we have made this raw data available. For larger datasets,see the Stanford Digital Michelangelo Project Archive.
Even if you start with real range data, if your goal is surface reconstruction,you should think twice about stripping away the mesh connectivity and treatingthe vertices as an unorganized point cloud. While this strategy may beappropriate for the data produced by some 3D capture technologies - such astime-of-flight scanners, it may be inappropriate for others - such asswept-plane laser triangulation systems. In these systems, the scannertypically examines a high-resolution image of the reflected laser line,deciding from its profile in this image whether two adjacent vertices should beconnected by a surface or not. Cyberware laser scanners do this. Thus, if youdiscard mesh connectivity, you are discarding real and possibly usefulinformation about the underlying surface.
-Notes by Marc Levoy
Contacting us
For questions and comments about our archive, send mail to:
scanrep-question at graphics dot stanford dot eduTo subscribe to the 3D Scanning Repository's email list, send mail to:
[email protected]with the message body:
subscribe graphics-scanrep-announce
Please acknowledge...
Please be sure to acknowledge the source of the data and models you take fromthis repository. In each of the listings below, we have cited the source ofthe range data and reconstructed models. You are welcome to use the data andmodels for research purposes. You are also welcome to mirror or redistributethem for free. Finally, you may publish images made using these models, or theimages on this web site, in a scholarly article or book - as long as credit isgiven to the Stanford Computer Graphics Laboratory. However, such models orimages are not to be used for commercial purposes, nor should they appear in aproduct for sale (with the exception of scholarly journals or books), withoutour permission.
Inappropriate uses of these models
As you browse this repository and think about how you might use our 3D modelsand range datasets, please remember that several of these artifacts havereligious or cultural significance. Aside from the buddha, which is areligious symbol revered by hundreds of millions of people, the dragon is asymbol of Chinese culture, the Thai statue contains elements of religioussignificance to Hindus, and Lucy is a Christian angel; statues like her arecommonly seen in Italian churches. Keep your renderings and other uses ofthese particular models in good taste. Don't animate or morph them, don'tapply Boolean operators to them, and don't simulate nasty things happening tothem (like breaking, exploding, melting, etc.). Choose another model for thesesorts of experiments. (You can do anything you want to the Stanford bunny orthe armadillo.)
The Stanford Models
Stanford BunnySource: Stanford University Computer Graphics Laboratory
Scanner: Cyberware 3030 MS
Number of scans: 10
Total size of scans: 362,272 points (about 725,000 triangles)
Reconstruction: zipper
Size of reconstruction: 35947 vertices, 69451 triangles
Comments: contains 5 holes in the bottom
Range data + zippered reconstruction:
Inventor and VRML versions of this model are available fromGeorgia Tech'slarge models archive.
A QSplat version of this model is available in theQSplat models archive.
Believe it or not, we also have aCT scan of the bunny. Check it out!
If you want to fly around the bunny, but don't need the model, try ScanView, our client / server rendering system.
We have also captured alight field of the bunny,using a gantry made fromLego Mindstorm.
This dataset was scanned in 1994 using the zippering technique described in[Turk94].
Here is longer, illustratedhistory of the Stanford bunny, fromGreg Turk'sweb pages at Georgia Tech.
Note about the bunny photograph:The bunny was bought and scanned in 1993-94. The color photograph (above) wastaken on April 1, 2003. The bits of gray plaster on the sides of the bunny'sfeet somehow appeared since the bunny was scanned; they are not present in the3D model. The chip on his left ear, however, is present in the model as well,although degraded in resolution.
Drill bitSource: Stanford University Computer Graphics Laboratory
Scanner: Cyberware 3030 MS
Number of scans: 12
Total size of scans: 50643 points (about 101,000 triangles)
Reconstruction: zipper and vrip
Size of zippered reconstruction: 881 vertices, 1288 triangles
Size of vripped reconstruction: 1961 vertices, 3855 triangles
Range data + zippered and vripped reconstructions:
This dataset first appeared in [Curless96].
Happy BuddhaSource: Stanford University Computer Graphics Laboratory
Download Game Zombie Vs Plants
Scanner: Cyberware 3030 MS + spacetime analysis
Number of scans: ~60
Total size of scans: 4,586,124 points (about 9,200,000 triangles)
Reconstruction: vrip (conservatively decimated)
Size of reconstruction: 543,652 vertices, 1,087,716 triangles
Comments: hole-free, but contains small bridges due to space carving,so its topological genus is larger than it appears
Range data:
happy_side.tar.gz (8.9 MB compressed, 35 MB uncompressed)
happy_back.tar.gz (8.1 MB compressed, 32 MB uncompressed)
happy_fillers.tar.gz (2.2 MB compressed, 9.0 MB uncompressed)
happy_backdrop.tar.gz (22 MB compressed, 89 MB uncompressed)
- Vripped reconstruction:
- happy_recon.tar.gz (14 MB compressed, 56 MB uncompressed)
Tango Failed To Download Game Catch Bunny Video
Inventor and VRML versions of this model are available fromGeorgia Tech'slarge models archive.
A QSplat version of this model is available in theQSplat models archive.
A voxel array representationof this model (i.e. a Stanford VRI file) is available on the web page of ourVolfill software package.
If you want to fly around the buddha, but don't need the model, try ScanView, our client / server rendering system.
This dataset first appeared in [Curless96].
Using the buddha model:Please remember that the buddha is a religious symbol. See our reminder aboveabout inappropriate uses of this model.
DragonSource: Stanford University Computer Graphics Laboratory
Scanner: Cyberware 3030 MS + spacetime analysis
Number of scans: ~70
Total size of scans: 2,748,318 points (about 5,500,000 triangles)
Reconstruction: vrip (conservatively decimated)
Size of reconstruction: 566,098 vertices, 1,132,830 triangles
Comments: contains numerous small holes
Range data:
dragon_side.tar.gz (4.2 MB compressed, 16 MB uncompressed)
dragon_up.tar.gz (5.7 MB compressed, 24 MB uncompressed)
dragon_fillers.tar.gz (6.7 MB compressed, 26 MB uncompressed)
dragon_backdrop.tar.gz (11 MB compressed, 44 MB uncompressed)
- Vripped reconstruction:
- dragon_recon.tar.gz (11 MB compressed, 43 MB uncompressed)
Inventor and VRML versions of this model are available fromGeorgia Tech'slarge models archive.
A QSplat version of this model is available in theQSplat models archive.
Light fields made from renderings of this model are available in theStanford Light Fields Archive.
This dataset first appeared in [Curless96].
Using the dragon:Please remember that the dragon is a symbol of Chinese culture. See ourreminder above about inappropriate uses of this model.
ArmadilloSource: Stanford University Computer Graphics Laboratory
Scanner: Cyberware 3030 MS
Number of scans: 114 (but only 60-70 were used in vripped model)
Total size of scans: 3,390,515 points (about 7,500,000 triangles)
Reconstruction: vrip (conservatively decimated)
Size of reconstruction: 345,944 triangles
Range data:
- Vripped reconstruction:
- Armadillo.ply.gz (4 MB compressed, 7 MB uncompressed)
This dataset first appeared in [Krishnamurthy96].
LucySource: Stanford University Computer Graphics Laboratory
Scanner:Stanford Large Statue Scanner
Number of scans: 47
Total size of scans: 58,241,932 points (approx 116 million triangles)
Reconstruction: vrip at 0.5 mm, holefilling
Size of reconstruction: 14,027,872 vertices, 28,055,742 triangles
Comments: hole-free, but contains small bridges due to space carving,so its topological genus is larger than it appears.
It may also have a few topological problems,making it not a proper manifold.Thanks to theChaos Groupfor the rendering above.
Range data:
Note about this range dataset:Lucy was scanned on two separate occasions. The raw range data(lucy_scans.tar.gz) and the VRIPped reconstruction (lucy.tar.gz) unfortunatelydo not correspond to the same scan of the statue. Moreover, the raw range datawas never aligned, so the *.xf transform files in lucy_scans.tar.gz (as well asthose in lucysd.tar.gz in the same directory) do not register the scanstogether.
Vripped reconstruction:
A QSplat version of this model is available in theQSplat models archive.
Using Lucy:Please remember that Lucy is a Christian angel. See our reminder above aboutinappropriate uses of this model.
Feel free, however, to build a lego replica of Lucy, as David Winkler has done.Check out his explanation of theconversion process. You can also download theplansand build it yourself.
The XYZ RGB models
Asian DragonScan data of a dragon sculpture constructed from wood pulp resin. Approx. 20cm x 8cm x 9cm.
Source: XYZ RGB Inc.
Scanner: XYZ RGB
Number of scans: 18
Scan Resolution: 100 um
Total size of scans: 6,300,000 points (about 12,600,000 triangles)
Size of merged model: 3,609,455 vertices, 7,218,906 triangles
Comments: watertight & uncompressed
Reconstructed model:
Using the dragon:Please remember that the dragon is a symbol of Chinese culture. See ourreminder above about inappropriate uses of this model.
Vellum manuscriptVellum manuscript. Approx. 22 cm x 30 cm.
Source: XYZ RGB Inc.
Scanner: XYZ RGB
Number of scans: 3
Scan Resolution: 100 um
Total size of scans: 2,368,123 points (about 4,750, 000 triangles)
Size of merged model: 2,152,840 vertices, 4,305,679 triangles
Comments: watertight & uncompressed
Reconstructed model:
This illuminated manuscript is a page in Latin from the Book of Hours, Rouen,c. 1460. The scan was made for the paper [Gardner03].
Thai StatueScan data of a resin statue. Approx. 40cm x 8cm x 8cm.
Source: XYZ RGB Inc.
Scanner: XYZ RGB
Number of scans: 36
Scan Resolution: 100 um
Total Size of scans: 34,500,000 points (about 69,000,000 triangles)
Size of merged model: 19,400,000 vertices (38,800,000 triangles)
Size of model provided: 5,000,000 vertices (10,000,000 triangles)
Comments: This model is provided in its decimated form of 10 million polygons
Reconstructed model:
Using this model:This statue includes elements of Hindu religious significance. See ourreminder above about inappropriate uses of this model.
Modelsfrom theStanford Digital Michelangelo Projectare available here.Models in QSplat format, including many of the models listed above,are available here.
Another site with a collection of large geometric models is Greg Turk'sLarge Geometric Models Archive at the Georgia Institute of Technology.Links to various pages of that archive are sprinkled throught this web page.
Citations
[Curless96] A Volumetric Method for Building Complex Models from Range Images
Brian Curless and Marc Levoy
Computer Graphics (SIGGRAPH 1996 Proceedings)
[Gardner03]Linear Light Source Reflectometry
Andrew Gardner, Chris Tchou, Tim Hawkins, Paul Debevec
Computer Graphics (SIGGRAPH 2003 Proceedings)
[Krishnamurthy96] Fitting Smooth Surfaces to Dense Polygon Meshes
Venkat Krishnamurthy and Marc Levoy
Computer Graphics (SIGGRAPH 1996 Proceedings)
[Turk94] Zippered Polygon Meshes from Range Images
Greg Turk and Marc Levoy
Computer Graphics (SIGGRAPH 1996 Proceedings)