Unsupervised 3D Object Recognition and Reconstruction in Unordered Datasets

Authors:
M. Brown;D. G. Lowe
Affiliations:
University of British Columbia;University of British Columbia
Venue:
3DIM '05 Proceedings of the Fifth International Conference on 3-D Digital Imaging and Modeling
Year:
2005

Citing 0
Cited 35

Photo tourism: exploring photo collections in 3D

ACM SIGGRAPH 2006 Papers
Photographing long scenes with multi-viewpoint panoramas

ACM SIGGRAPH 2006 Papers
Robust multi-view feature matching from multiple unordered views

Pattern Recognition
Interactive 3D architectural modeling from unordered photo collections

ACM SIGGRAPH Asia 2008 papers
Modeling the World from Internet Photo Collections

International Journal of Computer Vision
Low-cost orthographic imagery

Proceedings of the 16th ACM SIGSPATIAL international conference on Advances in geographic information systems
Landmark-based pedestrian navigation from collections of geotagged photos

Proceedings of the 7th International Conference on Mobile and Ubiquitous Multimedia
Learning to generate novel views of objects for class recognition

Computer Vision and Image Understanding
Spatio-temporal constraints for on-line 3D object recognition in videos

Computer Vision and Image Understanding
Places clustering of full-length film key-framesusing latent aspect modeling over SIFT matches

IEEE Transactions on Circuits and Systems for Video Technology
A coaxial optical scanner for synchronous acquisition of 3D geometry and surface reflectance

ACM SIGGRAPH 2010 papers
Image mosaicing via quadric surface estimation with priors for tunnel inspection

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Toward automated generation of parametric BIMs based on hybrid video and laser scanning data

Advanced Engineering Informatics
Efficient structure from motion by graph optimization

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Stable structure from motion for unordered image collections

SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features

Advanced Engineering Informatics
Large-scale, dense city reconstruction from user-contributed photos

Computer Vision and Image Understanding
Scene reconstruction and visualization from internet photo collections

Scene reconstruction and visualization from internet photo collections
Sorting unorganized photo sets for urban reconstruction

Graphical Models
Imposing Semi-Local Geometric Constraints for Accurate Correspondences Selection in Structure from Motion: A Game-Theoretic Perspective

International Journal of Computer Vision
A harris-like scale invariant feature detector

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Analysing false positives and 3d structure to create intelligent thresholding and weighting functions for SIFT features

PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
Spatio-angular resolution tradeoffs in integral photography

EGSR'06 Proceedings of the 17th Eurographics conference on Rendering Techniques
Documentation and interpretation of an archeological excavation: an experience with dense stereo reconstruction tools

VAST'11 Proceedings of the 12th International conference on Virtual Reality, Archaeology and Cultural Heritage
Multiple view object cosegmentation using appearance and stereo cues

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Achievements and challenges in recognizing and reconstructing civil infrastructure

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis
Pipelined architecture for real-time cost-optimized extraction of visual primitives based on FPGAs

Digital Signal Processing
Generating the sparse point cloud of a civil infrastructure scene using a single video camera under practical constraints

Proceedings of the Winter Simulation Conference
Practical time bundle adjustment for 3d reconstruction on the GPU

ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part II
A Performance Evaluation of Volumetric 3D Interest Point Detectors

International Journal of Computer Vision
Fully Automatic Registration of Image Sets on Approximate Geometry

International Journal of Computer Vision
Robust trifocal tensor constraints for structure from motion estimation

Pattern Recognition Letters
A novel unsupervised approach for multilevel image clustering from unordered image collection

Frontiers of Computer Science: Selected Publications from Chinese Universities
A hybrid image-based modelling algorithm

ACSC '13 Proceedings of the Thirty-Sixth Australasian Computer Science Conference - Volume 135
Multi-object reconstruction from dynamic scenes: An object-centered approach

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a system for fully automatic recognition and reconstruction of 3D objects in image databases. We pose the object recognition problem as one of finding consistent matches between all images, subject to the constraint that the images were taken from a perspective camera. We assume that the objects or scenes are rigid. For each image we associate a camera matrix, which is parameterised by rotation, translation and focal length. We use invariant local features to find matches between all images, and the RANSAC algorithm to find those that are consistent with the fundamental matrix. Objects are recognised as subsets of matching images. We then solve for the structure and motion of each object, using a sparse bundle adjustment algorithm. Our results demonstrate that it is possible to recognise and reconstruct 3D objects from an unordered image database with no user input at all.