Multi-view Matching for Unordered Image Sets, or "How Do I Organize My Holiday Snaps?"

By Frederik Schaffalitzky, Andrew Zisserman. European Conference on Computer Vision, 2002

721 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7e81996384b030b580a0e02c0dc367d59c0c15ba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Discovering object categories in image collections (2005, methodology): “We use vector quantized SIFT descriptors [12] computed on affine covariant regions [13, 14, 16].”
Vision-based global localization and mapping for mobile robots (2005, background): “There has been considerable recent research on developing affine-invariant features [21], [24], but they have reduced stability to nonextreme affine changes compared to our features and have a much higher computational cost for detection.”
Randomized trees for real-time keypoint recognition (2005, background): “Since the pioneering work by Schmid and Mohr [1], the algorithms have become ever more robust to scale, viewpoint, illumination changes and partial occlusions [2, 3, 4, 5, 6, 7].”
Machine Learning for High-Speed Corner Detection (2006, background): “Recently, scale invariance has been extended to consider features which are invariant to affine transformations [14,16,17].”
Multi-image matching using multi-scale oriented patches (2005, neutral): “Invariant feature-based approaches to matching have been successfully applied to a wide range of problems, including object recognition [6], structure from motion[14], and panoramic image stitching [15].”
A sparse texture representation using local affine regions (2005, background): “Invariance to such transformations is highly desirable for many applications, including wide-baseline stereo matching [1, 40, 41, 45], indexing and retrieval in image and video databases [32, 42, 43, 44], and classi(cid:12)cation of images of materials [46, 47].”
SfM with MRFs: Discrete-Continuous Optimization for Large-Scale Structure from Motion (2013, neutral): “Current techniques for large-scale SfM from unordered photo collections [2], [4], [8], [5] make heavy use of bundle adjustment to solve a nonlinear optimization problem.”
Scene modelling, recognition and tracking with invariant image features (2004, methodology): “Therefore we apply a selective approach, similar to [21], which is linear in the number of images.”
What and Where: 3D Object Recognition with Accurate Pose (2006, methodology): “Therefore we apply a selective approach, similar to [20], which is linear in the number of images.”
CZECH TECHNICAL UNIVERSITY IN PRAGUE (2005, background): “Most of the state of the art techniques for 3D reconstruction from unordered image sets [35, 3, 42, 24] start the computation by performing exhaustive pairwise image matching in order to reveal the structure and connectivity of the data.”
Video data mining using configurations of viewpoint invariant regions (2004, background): “The approach taken in all these cases is to represent an image by a set of overlapping regions, each represented by a vector computed from the region’s appearance.”
Robust Rotation and Translation Estimation in Multiview Reconstruction (2007, background): “The Raglan scene [19] was captured on 46 images, 238 EGs were found (see details in section 6).”
Image sequence geolocation with human travel priors (2009, methodology): “Our work is related to previous efforts to organize photo collections, for example, through geometric alignment [16, 18], by clustering photos into sequences of events [4], or both [3].”
An Affine Invariant Salient Region Detector (2004, methodology): “In this paper we have presented a new region detector which is comparable to the state of the art [19,20] in terms of co-variance with viewpoint.”
SURF: Speeded Up Robust Features (2006, background): “An even larger variety of feature descriptors has been proposed, like Gaussian derivatives [16], moment invariants [17], complex features [18, 19], steerable filters [20], phase-based local features [21], and descriptors representing the distribution of smaller-scale features within the interest poi”