Randomized structure from motion based on atomic 3D models from camera triplets

Havlena, Michal; Torii, Akihiko; Knopp, Jan; Pajdla, Tomáš

doi:10.1109/cvpr.2009.5206677

Cited by 52 publications

(21 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiments to quantitatively measure its performance are in Sect. 4. We finally conclude in Sect.…”

Section: Introductionmentioning

confidence: 94%

See 1 more Smart Citation

A Critical Review of the Trifocal Tensor Estimation

Julià¹,

Monasse²

2018

Image and Video Technology

View full text Add to dashboard Cite

Abstract. We explore the advantages offered by the trifocal tensor in the pose estimation of a triplet of cameras as opposed to computing the relative poses pair by pair with the fundamental matrix. Theoretically, the trinilearities characterize uniquely three corresponding image points in a tighter way than the three epipolar equations and this translates in an increasing accuracy. However, we show that this initial improvement is not enough to have a remarkable impact on the pose estimation after bundle adjustment, and the use of the fundamental matrix with image triplets remains relevant.

show abstract

“…The experiments to quantitatively measure its performance are in Sect. 4. We finally conclude in Sect.…”

Section: Introductionmentioning

confidence: 94%

“…Theoretically, no extra geometric information about three views comes from considering additional views at once. Therefore, multi-view structure from motion pipelines always rely on initial view pairs [7,14,15] or triplets [4,8].…”

Section: Introductionmentioning

confidence: 99%

A Critical Review of the Trifocal Tensor Estimation

Julià¹,

Monasse²

2018

Image and Video Technology

View full text Add to dashboard Cite

show abstract

“…2010, Algorithm 1). For the 3D structure, they make use of the atomic 3D models from image triplets approach of Havlena, Torii, Knopp and Pajdla (2009), and grow the structure by using a prioritization queue, which orders the different tasks of either creating a new atomic 3D model or incorporating one image into a given 3D model (Havlena et al. 2010, Section 3).…”

Section: Structure Estimationmentioning

confidence: 99%

A survey of structure from motion.

Voroninski²,

et al. 2017

View full text Add to dashboard Cite

The structure from motion (SfM) problem in computer vision is to recover the three-dimensional (3D) structure of a stationary scene from a set of projective measurements, represented as a collection of two-dimensional (2D) images, via estimation of motion of the cameras corresponding to these images. In essence, SfM involves the three main stages of (i) extracting features in images (e.g. points of interest, lines,etc.) and matching these features between images, (ii) camera motion estimation (e.g. using relative pairwise camera positions estimated from the extracted features), and (iii) recovery of the 3D structure using the estimated motion and features (e.g. by minimizing the so-calledreprojection error). This survey mainly focuses on relatively recent developments in the literature pertaining to stages (ii) and (iii). More specifically, after touching upon the early factorization-based techniques for motion and structure estimation, we provide a detailed account of some of the recent cameralocationestimation methods in the literature, followed by discussion of notable techniques for 3D structure recovery. We also cover the basics of thesimultaneous localization and mapping(SLAM) problem, which can be viewed as a specific case of the SfM problem. Further, our survey includes a review of the fundamentals of feature extraction and matching (i.e. stage (i) above), various recent methods for handling ambiguities in 3D scenes, SfM techniques involving relatively uncommon camera models and image features, and popular sources of data and SfM software.

show abstract

“…Incremental approaches. Most of well-known SfM systems register cameras sequentially [3,38,39,43,44] or hierarchically [14,22,26] from pairwise relative motions. In order to minimize error accumulation, frequent intermediate bundle adjustment is required for both types of methods, which significantly reduces computation efficiency.…”

Section: Related Workmentioning

confidence: 99%

Linear Global Translation Estimation with Feature Tracks

Cui¹,

Jiang²,

Tang³

et al. 2015

Procedings of the British Machine Vision Conference 2015

View full text Add to dashboard Cite

Street SevilleResult from [4] Our resultResult from [3] Our resultFigure 1: 1DSFM [4] and triplet-based methods (e.g. [3]) require strong association among images. As shown in the left, they fail for images with weak association. In comparison, as shown in the right, the results from our method do not suffer from such problems.Global structure-from-motion (SfM) algorithms register all cameras simultaneously, which are potentially more efficient and less prone to drifting than incremental SfM methods. Global SfM methods often solve the camera orientations and positions separately. This paper focuses on the problem of global position (i.e. translation) estimation.Essential matrix based global translation estimation methods (e.g. [1]) usually degenerate at collinear camera motion because the translation scale is not determined by an essential matrix. Trifocal tensor based methods (e.g. [3]) usually rely on a strongly connected camera-triplet graph, where two triplets are connected by their common edge. The 3D reconstruction will distort or break into disconnected components when such strong association among images does not exist. The recent 1DSfM method [4] designs a smart filter to discard outlier essential matrices and solves scene points and cameras together by enforcing orientation consistency. However, this method requires abundant association between input images, e.g. ∼ O(n 2 ) essential matrices for n cameras, which is more suitable for Internet images and often fails on sequentially captured data.The data association problem of [4] and [3] is exemplified in Figure 1. The Street example on the top is a sequential data where each image is only matched upto 4 neighbors. 1DSfM fails on this example due to insufficient image association. In the Seville example on the bottom, those Internet images are mostly captured from two viewpoints (see the two representative sample images) with weak affinity between images at different viewpoints. This weak data association causes seriously distorted reconstruction for the triplet-based method in [3]. This paper introduces a direct linear algorithm to address the presented challenges. It avoids degeneracy at collinear motion and deals with weakly associated data. Our method capitalizes on constraints from essential matrices and feature tracks. As shown in Figure 2 (a), the

show abstract

Randomized structure from motion based on atomic 3D models from camera triplets

Cited by 52 publications

References 22 publications

A Critical Review of the Trifocal Tensor Estimation

A Critical Review of the Trifocal Tensor Estimation

A survey of structure from motion.

Linear Global Translation Estimation with Feature Tracks

Contact Info

Product

Resources

About