msavva / pigraphs Goto Github PK
View Code? Open in Web Editor NEWPiGraphs: Learning Interaction Snapshots from Observations
Home Page: http://graphics.stanford.edu/projects/pigraphs
License: Other
PiGraphs: Learning Interaction Snapshots from Observations
Home Page: http://graphics.stanford.edu/projects/pigraphs
License: Other
Hi,
I'm wondering if it is possible to get access to the pose annotated raw data that was used to generate the .ply files for the scenes. I can see the recording for interactions but no video or frame data for the scene that was scanned before the interaction. Thanks!
Best,
Nilesh
Hi Manolis,
I have some questions regarding the skeleton format. I am trying to build a skeleton viewer where the input is the joints' orientation angles and the output is the skeleton in 3D space. So can you please point me to the relevant segments of the code, and also can you elaborate on these questions:
Hi Savva,
I'm running your PiGraph code, but stuck in JavaApps/target/SceneGrok-0.0.1.jar.
Actually, we can't find the SceneGrok in PiGraph code. Could you give me some tips?
Thank you very much :)
Hi @msavva
I am trying to register the depth and rgb frames in the dataset. I managed to find what it seems to be the depth sensor intrinsics in
Line 16 in db88ee5
But I can't find the rgb sensor intrinscis or the extrinsics between the two sensors. Would you be able help with that?
Thanks in advance.
cannot get the data when click http://dovahkiin.stanford.edu/etherion/data/pigraphs/pigraphs-data.zip
I'm running the v synth command in vizzer.exe using the provided vbox package and get into several errors as the following log shows:
Welcome to SceneGrok! Type help for usage info.
[ScanDatabase] 26 scans loaded from C:/Users/msavva/Desktop/data//scans/scenes.json
[ScanDatabase] Error loading from C:/Users/msavva/Desktop/data//scans-cornell/scenes.json
[ModelDatabase] modelsDir does not exist: C:/Users/msavva/Desktop/data/../models/repositories/g3dw/models/
[ModelDatabase] modelsMetadataFile does not exist at: C:/Users/msavva/Desktop/data/../models/data-tables/models3d.wssAligned.json
initModelDatabase : 0.040s
[error] [main]: core\SceneDatabase.cpp:19[sg::core::SceneDatabase::SceneDatabase] [SceneDatabase] Error loading from C:/Users/msavva/Desktop/data/recon2scene-items.csv
[error] [main]: core\MotionDatabase.cpp:42[sg::core::MotionDatabase::MotionDatabase] [MotionDatabase] Error loading index from: V:/data/external/cmumocap/asfamc/index.csv
[ModelAnnotationDatabase] loaded 436 annotations in initModelAnnotationDatabase : 0.020s
[ObjectLabeler] CategoryMapFile: ../../data/categories.csv : backpack->Backpack, bed->Bed, book->Book, bookcase->Bookcase, chair->Chair, coffeetable->CoffeeTable, cpu->Desktop, co
UI pipes created
[info] [main]: Waiting...
[info] [main]: Waiting for console thread...
[D3D11Vizzer] Initializing ahouse...[Scan:ahoused...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from ahoused.segs...
[info] []: updated segmentation: 417, 42
(living room)[D3D11Vizzer] Initializing Recording ahouse_mati5_2014-05-16-19-45-44...[info] []: [Recording: ahouse_mati5_2014-05-16-19-45-44.json, nSkels: 2752, time: 183.585s]
[+interactions][Recording] Computing actSegs: ahouse_mati5_2014-05-16-19-45-44...done.
[+colorVideo] [+depthVideo] done.
done.
[D3D11Vizzer] Initializing Recording ahouse_mati5_2014-05-16-19-45-44...[+colorVideo] [+depthVideo] done.
v synth
[info] []: Loading CategoryCounts from C:/Users/msavva/Desktop/data/stats/supportParentGivenChild.csv
[error] []: core\ScenePriors.cpp:165[sg::core::CategoryCounts::load] Cannot load file C:/Users/msavva/Desktop/data/stats/supportParentGivenChild.csv
[info] []: Loading CategoryCounts from C:/Users/msavva/Desktop/data/stats/supportChildGivenParent.csv
[error] []: core\ScenePriors.cpp:165[sg::core::CategoryCounts::load] Cannot load file C:/Users/msavva/Desktop/data/stats/supportChildGivenParent.csv
[info] []: Loading CategoryHierarchy from C:/Users/msavva/Desktop/data/subcategories.txt
[error] []: core\ScenePriors.cpp:75[sg::core::CategoryHierarchy::load] Cannot load file C:/Users/msavva/Desktop/data/subcategories.txt
[info] []: Loading interaction database from ../cache/interactionDb.cached
[info] []: Loading skeleton database from ../cache/skeletonsDb.cached
[info] []: Finalizing skeleton database
[info] []: [SkeletonDatabase] Loaded 14128 skeletons, 83 distributions
Loading all scans with recordings...[Scan:3bcommonsd...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from 3bcommonsd.segs...
[info] []: updated segmentation: 151, 12
[Scan:3bHallwayd...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from 3bHallwayd.segs...
[info] []: updated segmentation: 79, 8
[Scan:gates250d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates250d.segs...
[info] []: updated segmentation: 431, 327
[Scan:gates360d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates360d.segs...
[info] []: updated segmentation: 217, 19
[Scan:gates381ad...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates381ad.segs...
[info] []: updated segmentation: 421, 45
[Scan:gates381d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates381d.segs...
[info] []: updated segmentation: 684, 420
[Scan:gates386d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates386d.segs...
[info] []: updated segmentation: 162, 29
[Scan:gates392d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates392d.segs...
[info] []: updated segmentation: 251, 70
[Scan:gates400d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates400d.segs...
[info] []: updated segmentation: 298, 73
[Scan:gates500d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates500d.segs...
[info] []: updated segmentation: 145, 67
[Scan:gates503d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from gates503d.segs...
[info] []: updated segmentation: 142, 10
[Scan:living3d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from living3d.segs...
[info] []: updated segmentation: 969, 543
[Scan:livingd...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from livingd.segs...
[info] []: updated segmentation: 519, 117
[Scan:sga15-apt500bedroomd...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from sga15-apt500bedroomd.segs...
[info] []: updated segmentation: 369, 186
[Scan:sga15-apt500d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from sga15-apt500d.segs...
[info] []: updated segmentation: 527, 96
[Scan:sga15-gates200Hallwayd...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from sga15-gates200Hallwayd.segs...
[info] []: updated segmentation: 271, 60
[Scan:sga15-gates372d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from sga15-gates372d.segs...
[info] []: updated segmentation: 366, 92
[Scan:sga15-gates381d...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from sga15-gates381d.segs...
[info] []: updated segmentation: 451, 107
[Scan:sga15-michaeld...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from sga15-michaeld.segs...
[info] []: updated segmentation: 421, 140
[Scan:sga15-phoned...[info] []: Recomputing object maps and bounding boxes from segment group bounding boxes
[info] []: segments from sga15-phoned.segs...
[info] []: updated segmentation: 256, 190
Done.
[info] []: Extracting centroids...
[warning] []: Skipping centroids for group: Head since only 0 segments activated.
[warning] []: Skipping centroids for group: Torso since only 1 segments activated.
D=-3.41119e-016 0 0 0 0
0 -1.78688e-016 0 0 0
0 0 3.0658e-017 0 0
0 0 0 0.743995 0
0 0 0 0 2.58934
An unexpected C++ error has occurred: java.lang.NoClassDefFoundError: edu/stanford/graphics/wekautils/Clustering
It seems like some files are missing, e.g., scans-cornell/scenes.json, but I didn't find them in the dataset. I cannot see the synthesized snapshot and hope to ask how to solve the errors.
Hi,
Getting mLibExternal to compile (on Ubuntu, GCC 4.9.4) is quite tricky, with some problems definitely not being a compiler problem. Is there a newer version of it online somewhere?
std::ostream and std::istream does not seem take boost::asio::streambuf* and ios::binary as 2constructor parameters, remove the openmode?:
mLib/include/ext-boost/serialization.h:38:14: error: no matching function for call to ‘std::basic_ostream<char>::basic_ostream(boost::asio::streambuf*, const openmode&)’ , m_ia(m_is) { }
mLib/include/ext-boost/serialization.h:39:14: error: no matching function for call to ‘std::basic_ostream<char>::basic_ostream(boost::asio::streambuf*, const openmode&)’ , m_ia(m_is) { }
mLib/include/ext-boost/serialization.h:245:41: error: no matching function for call to ‘std::basic_ostream<char>::basic_ostream(boost::asio::streambuf*, const openmode&)’ (with Boost version 1.58)
toJSON does not seem to be able to get resolved for vec<int64_t> (add template <typename T> ostream& toJSON(ostream& os, const T& x);
at line 73 in json.h):
In file included from libsg/segmentation/Part.h:7:0,
from segmentation/SegmentGroup.h:8,
from libsg/core/Scan.h:8,
from libsg/core/Recording.cpp:8:
libsg/io/json.h: In instantiation of ‘std::ostream& sg::io::toJSON(std::ostream&, sg::vec<Vector3T>&) [with T = long int; std::ostream = std::basic_ostream<char>; sg::vec<Vector3T> = std::vector<long int, std::allocator<long int> >]’:
libsg/core/Recording.cpp:254:59: required from here
libsg/io/json.h:90:20: error: no matching function for call to ‘toJSON(std::ostream&, const value_type&)’
toJSON(os, x[i]) << ",";
^
missing std:: from endl:
mLib/include/core-math/PCA.cpp:83:45: error: ‘endl’ was not declared in this scope std::cout << "Computing eigensystem..." << endl;
mLib/include/core-math/PCA.cpp:105:104: error: ‘endl’ was not declared in this scope std::cout << "Energy at " << dimIndex + 1 << " terms: " << cumulativeEnergy / sum * 100.0f << "%" << endl;
_means.size instead of dimension:
mLib/include/core-math/PCA.cpp:141:20: error: ‘dimension’ was not declared in this scope result.resize(dimension);
need explicit std namespace around member class: namespace std { struct hash<...>{}; }
mLib/include/core-util/sparseGrid3.h:6:13: error: specialization of ‘template<class _Tp> struct std::hash’ in different namespace [-fpermissive] struct std::hash<ml::vec3i> : public std::unary_function<ml::vec3i, size_t> {
need this->
or using Grid3<FLoatType>::getDimX;
for parent functions:
mLib/include/core-base/distanceField3.h:142:48: error: there are no arguments to ‘getDimX’ that depend on a template parameter, so a declaration of ‘getDimX’ must be available [-fpermissive] vec3<FloatType> maxBound((FloatType)getDimX() - 1, (FloatType)getDimY() - 1, (FloatType)getDimZ() - 1);
mLib/include/core-base/distanceField3.h:161:51: error: there are no arguments to ‘getDimX’ that depend on a template parameter, so a declaration of ‘getDimX’ must be available [-fpermissive] (FloatType)res.getDimX() / (FloatType)getDimX(),
template <typename T> class NumericGrid : public Grid<T> { using Grid<T>::m_data; using Grid<T>::m_rows; using Grid<T>::m_cols;
template <typename T, typename NumT = float> class BinnedGrid : public Grid<T> { using Grid<T>::allocate; using Grid<T>::m_rows; using Grid<T>::m_cols;
missing ml::
in front of vec3f
:
/mLib/include/ext-boost/serialization.h:182:5: error: ‘vec3f’ was not declared in this scope vec3f v[4];
NumericGrid::minElement()
needs to use iColMin
instead of iColMax
;
Predeclared enum not defined (just comment it out):
libsg/libsg.h:152:6: error: use of enum ‘PartType’ without previous declaration enum PartType;
Need #include "util/eigenutil.h"; #include "io/json.h";
at the top of Part.h:
libsg/segmentation/Part.h:85:25: error: ‘eigenutil’ is not a namespace-name using namespace sg::eigenutil;
libsg/segmentation/Part.h:89:5: error: ‘toFloatVector’ is not a member of ‘sg::io’ sg::io::toFloatVector(obbIn["centroid"], ¢roidArr);
Useless typedef (comment it out):
libsg/segmentation/SegmentGroup.h:284:21: error: declaration of ‘typedef sg::segmentation::VecSegPtr sg::segmentation::SegmentGroupsRecord::VecSegPtr’ [-fpermissive] typedef VecSegPtr VecSegPtr;
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.