Recognising panoramas

By Matthew A. Brown, David G. Lowe. 2003

1,060 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (2017, background): “We note that such a multi-resolution pipeline is a wellestablished practice in computer vision [4] and two-scale is often enough [3].”
A Linear Time Histogram Metric for Improved SIFT Matching (2008, methodology): “The SIFT descriptor has proven to be successful in applications such as object recognition [3, 7–9], object class detection [10–12], image retrieval [13–16], robot localization [17], building panoramas [18] and image classification [19].”
On the Use of SIFT Features for Face Authentication (2006, background): “Recently, theScale Invariant Feature Transform(SIFT) has emerged as a cut edge methodology in general object recognition as well as for other machine vision applications [13, 11, 12, 10, 5].”
ASIFT: A New Framework for Fully Affine Invariant Image Comparison (2009, background): “…[10, 40, 50, 61, 15, 52, 65, 41] and detection [14, 46], robot localization [6, 53, 47, 43], image registration [64], image retrieval [16], motion tracking [59, 20], 3D modeling and reconstruction [49, 62], building panoramas [1, 7], photo management [63, 21, 55, 9], and symmetry detection [30].”
Automatic Panoramic Image Stitching using Invariant Features (2007, methodology): “In addition to providing more detail, this paper extends our previous work in the area (Brown and Lowe, 2003) by introducing gain compensation and automatic straightening steps.”
High performance imaging using large camera arrays (2005, methodology): “We use Autostitch [Brown and Lowe 2003]) to create our image mosaics.”
The patch transform and its applications to image editing (2008, background): “Because we seek to place image patches together in a composite, our work relates to larger spatial scale versions of that task, including Auto Collage [24] and panorama stitching [5], although with different goals.”
Deep feature synthesis: Towards automating data science endeavors (2015, background): “These types of features can be successfully generalized for many problems and applications in machine vision, including object recognition and panorama stitching [7].”
Fast Neighborhood Graph Search Using Cartesian Concatenation (2013, background): “It is also a crucial step in many vision and graphics problems, such as shape matching [13], object retrieval [29], feature matching [8, 35], texture synthesis [23], image completion [16] and so on.”
Rotational Projection Statistics for 3D Local Surface Description and Object Recognition (2013, background): “t recognition is to correctly identify the objects that are present in a scene and recover their poses (i.e., position and orientation) (Mian et al., 2006b). Beyond object recognition from 2D images (Brown and Lowe, 2003; Lowe, 2004; Mikolajczyk and Schmid, 2004), 3D objectrecognitionhasbeenextensiv”
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].”
Matching with PROSAC - progressive sample consensus (2005, background): “The constraint is typically checked ex-post in standard approaches [1].”
Unsupervised 3D object recognition and reconstruction in unordered datasets (2005, methodology): “Such algorithms look for structure in the data, using, for example, a probabilistic ‘constellation model’ [7] or geometric constraints arising from the image formation process [5, 15, 14].”
A 3-dimensional sift descriptor and its application to action recognition (2007, methodology): “Much work has been done using the original SIFT descriptor [8, 9] for tasks such as object recognition [8, 9], point tracking [11, 7], panorama creation [2], etc.”
Constructing image panoramas using dual-homography warping (2011, background): “Image mosaicing is a well-studied area in computer vision (representative works include [18, 19, 6, 7, 9, 23]); for an excellent survey see [22].”
Recursive estimation of generative models of video (2006, neutral): “Our work is similar to the mosaicking work [7] on mosaicbased representations of video sequences.”