Comments (4)
Thank you for posting here. See that step 4 did not provided meaningful match. It is most likely that your camera model is not in the sensor database we have. You can use "-f value" on SfM init image listing to set a focal prior for your dataset. You can set the value as 1.2 * max(width, height) of the image. Let me know how it goes. We are here to help!
from openmvg.
Can you specify where should we add this -f value, which command or which place in the source code? I am having the same exact error but by logs are like this -
Using input dir : /home/megumi/saatvik/SphereGlue/images
output_dir : /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental
- Intrinsics analysis
INFO: [main_SfMInit_ImageListing.cpp:197] You called : /home/megumi/saatvik/openMVG_Build/Linux-x86_64-RELEASE/openMVG_main_SfMInit_ImageListing
--imageDirectory /home/megumi/saatvik/SphereGlue/images
--sensorWidthDatabase /home/megumi/saatvik/openMVG/src/software/SfM/../../openMVG/exif/sensor_width_database/sensor_width_camera_database.txt
--outputDirectory /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches
--focal -1
--intrinsics
--camera_model 3
--group_camera_model 1
--use_pose_prior 0
--prior_weights 1.0;1.0;1.0
--gps_to_xyz_method 0
INFO: [loggerprogress.hpp:79] [- Listing images -] 100%
INFO: [main_SfMInit_ImageListing.cpp:478] SfMInit_ImageListing report:
listed #File(s): 3
usable #File(s) listed in sfm_data: 3
usable #Intrinsic(s) listed in sfm_data: 0 - Compute features
INFO: [main_ComputeFeatures.cpp:120] You called :
/home/megumi/saatvik/openMVG_Build/Linux-x86_64-RELEASE/openMVG_main_ComputeFeatures
--input_file /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/sfm_data.json
--outdir /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches
--describerMethod SIFT
--upright 0
--describerPreset NORMAL
--force 0
--numThreads 0
INFO: [loggerprogress.hpp:79] [- EXTRACT FEATURES -] 100%
INFO: [main_ComputeFeatures.cpp:343] Task done in (s): 0
3. Compute matching pairs
You called:
/home/megumi/saatvik/openMVG_Build/Linux-x86_64-RELEASE/openMVG_main_PairGenerator
--input_file : /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/sfm_data.json
--output_file : /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/pairs.bin
Optional parameters
--pair_mode : EXHAUSTIVE
--contiguous_count : -1
Loading scene.Computing pairs.
Saving pairs.
-
Compute matches
INFO: [main_ComputeMatches.cpp:113] You called :
/home/megumi/saatvik/openMVG_Build/Linux-x86_64-RELEASE/openMVG_main_ComputeMatches
--input_file /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/sfm_data.json
--output_file /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/matches.putative.bin
--pair_list /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/pairs.bin
Optional parameters:
--force 0
--ratio 0.8
--nearest_matching_method AUTO
--cache_size unlimited
--preemptive_feature_used/count 0 / 200
INFO: [loggerprogress.hpp:79] [- Regions Loading -] 100%
INFO: [main_ComputeMatches.cpp:216] - PUTATIVE MATCHES -
INFO: [main_ComputeMatches.cpp:225] PREVIOUS RESULTS LOADED; #pair: 3
INFO: [main_ComputeMatches.cpp:365] #Putative pairs: 3
INFO: [graph_stats.hpp:53] Graph statistics:
#nodes: 3
#cc: 1
#singleton: 0
Node degree statistics: min: 2, max: 2, mean: 2, median: 2 -
Filter matches
INFO: [main_GeometricFilter.cpp:131] You called :
/home/megumi/saatvik/openMVG_Build/Linux-x86_64-RELEASE/openMVG_main_GeometricFilter
--input_file: /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/sfm_data.json
--matches: /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/matches.putative.bin
--output_file: /home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/matches/matches.f.bin
Optional parameters:
--input_pairs
--output_pairs
--force false
--geometric_model f
--guided_matching 0
--cache_size unlimited
INFO: [loggerprogress.hpp:79] [- Regions Loading -] 100%
INFO: [graph_stats.hpp:53] Graph statistics:
#nodes: 3
#cc: 1
#singleton: 0
Node degree statistics: min: 2, max: 2, mean: 2, median: 2
INFO: [main_GeometricFilter.cpp:383] Task done in (s): 0
INFO: [main_GeometricFilter.cpp:386]
Export Adjacency Matrix of the pairwise's geometric matches -
Do Sequential/Incremental reconstruction
INFO: [main_SfM.cpp:157]
Structure from Motion:
INFO: [loggerprogress.hpp:79] [- Features Loading -] 100%
INFO: [sequential_SfM.cpp:278] Track building
INFO: [sequential_SfM.cpp:281] Track filtering
INFO: [sequential_SfM.cpp:283] Track export to internal struct
INFO: [sequential_SfM.cpp:309]
-- Tracks Stats --
Tracks number: 125
Images Id:
0, 1, 2,
TrackLength, Occurrence
2 111
3 14
ERROR: [sequential_SfM.cpp:110] Unable to choose an initial pair, since there is no defined intrinsic data.
INFO: [sequential_SfM.cpp:173] Cannot find a valid initial pair - stop reconstruction.
- Colorize Structure
ERROR: [main_ComputeSfM_DataColor.cpp:69] The input SfM_Data file "/home/megumi/saatvik/SphereGlue/images_mvg_sfm_incremental/reconstruction_sequential/sfm_data.bin" cannot be read.
from openmvg.
@saatvikmah if you use sphereglue you most likely intend to use panoramic images and so most likely need to setup the camera model to be panoramic/spherical.
from openmvg.
Where? to set the camera model
from openmvg.
Related Issues (20)
- Stellar vs Global mode of construction HOT 1
- with CERES: 2.2.0, “openMVG_main_SfM” terminated abruptly HOT 1
- about reprojrction error and Residuals HOT 1
- Trying to load custom superpoint features and descriptors HOT 2
- What does “AUTO” mean in matching algorithm? HOT 3
- Problem in Gcp registration HOT 5
- error from ceres when building HOT 1
- fatal error: Eigen/Dense: No such file or directory while building HOT 11
- triangulation with know poses HOT 2
- SfM error HOT 1
- Reconstruct mulitple sub-models from an image set? HOT 2
- openMVG_main_SfM runs very slow on 2 socket AMD EPYC system HOT 3
- Can Triangulate2View used if the poses are known ? HOT 2
- The exif data i.e., focal length of an image is missing
- Unable to convert sfm_perspective_data.bin to OpenMVS
- retrieving point cloud after SfM from `sfm_data.bin` HOT 2
- How to use existing reconstruction to constraint a new reconstruction
- Known partial camera pose relationships HOT 1
- `openMVG_main_openMVGSpherical2Cubic` causes segmentation fault HOT 5
- SfM from known poses
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from openmvg.