Reassembling fractured objects by geometric matching

Huang, Qixing; Flöry, Simon; Gelfand, Natasha; Hofer, Michaël; Pottmann, Helmut

doi:10.1145/1179352.1141925

Cited by 61 publications

(37 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neugebauer [1997], Benjemaa and Schmitt [1998], Williams and Bennamoun [2000], Li and Guskov [2005], and Krishnan et al [2005] describe closed-form methods for determining the alignment of all scans simultaneously, while Wen et al [2005] simultaneously solve for both rigid pose and target feature positions, assuming corre-spondences are known. Huang et al [2006] incorporate a nonintersection constraint during global registration. Our method is most similar to Pulli's: we scale to large datasets by dividing registration into two phases, a computationally expensive yet parallelizable pairwise alignment for all pairs of overlapping scans followed by a global optimization based only on point pairs computed during the first phase.…”

Section: Previous Workmentioning

confidence: 99%

Global non-rigid alignment of 3-D scans

Brown

Rusinkiewicz

2007

ACM SIGGRAPH 2007 Papers

121

113

View full text Add to dashboard Cite

Figure 1: Using non-rigid global alignment techniques, we are able to preserve more surface detail with fewer merging artifacts, as seen in closeups of the upper-left edge of this Forma Urbis Romae fragment. (c) Using non-rigid alignment (section 3.3) improves alignment enough to eliminate most surface noise. (d) Incorporating locally weighted ICP-based feature correspondences (section 3.2) further improves detail alignment, notably eliminating double edges. AbstractA key challenge in reconstructing high-quality 3D scans is registering data from different viewpoints. Existing global (multiview) alignment algorithms are restricted to rigid-body transformations, and cannot adequately handle non-rigid warps frequently present in real-world datasets. Moreover, algorithms that can compensate for such warps between pairs of scans do not easily generalize to the multiview case. We present an algorithm for obtaining a globally optimal alignment of multiple overlapping datasets in the presence of low-frequency non-rigid deformations, such as those caused by device nonlinearities or calibration error. The process first obtains sparse correspondences between views using a locally weighted, stability-guaranteeing variant of iterative closest points (ICP). Global positions for feature points are found using a relaxation method, and the scans are warped to their final positions using thin-plate splines. Our framework efficiently handles large datasets -thousands of scans comprising hundreds of millions of samples -for both rigid and non-rigid alignment, with the nonrigid case requiring little overhead beyond rigid-body alignment. We demonstrate that, relative to rigid-body registration, it improves the quality of alignment and better preserves detail in 3D datasets from a variety of scanners exhibiting non-rigid distortion. *

show abstract

Section: Previous Workmentioning

confidence: 99%

Global non-rigid alignment of 3-D scans

Brown

Rusinkiewicz

2007

ACM SIGGRAPH 2007 Papers

121

113

View full text Add to dashboard Cite

show abstract

“…To select the feature points, shape descriptors are used, including the global harmonic shape descriptors,16 light field descriptors, 17 integral volume descriptors,18 curvature-based local descriptors,19 and integral invariant multi-scale surface characteristics 20. A priority-based search would be performed to match the surface features between two geometric models 21.…”

Section: Background and Related Workmentioning

confidence: 99%

Image guided medialization laryngoplasty

Jin¹,

Baek²,

Hahn³

et al. 2009

Computer Animation & Virtual

View full text Add to dashboard Cite

Techniques that originate in computer graphics and computer vision have found prominent applications in the medical domain. In this paper, we have seamlessly developed techniques from computer graphics and computer vision together with domain knowledge from medicine to develop an image guided surgical system for medialization laryngoplasty. The technical focus of this paper is to register the preoperative radiological data to the intraoperative anatomical structure of the patient. With careful analysis of the real-world surgical environment, we have developed an ICP-based partial shape matching algorithm to register the partially visible anatomical structure to the preoperative CT data. We extracted distinguishable features from the human thyroid cartilage surface and applied image space template matching to find the initial guess for the shape matching. The experimental result shows that our feature-based partial shape matching method has better performance and robustness compared with original ICP-based shape matching method. Although this paper concentrates on the medialization laryngoplasty procedure, its generality makes our methods ideal for future applications in other image guided surgical areas.

show abstract

“…In this line, multiple descriptors that simplify the search process have been proposed based on curvature [12], [13] or integral invariants [14], [15]. To calculate the descriptor's alignment, there are techniques based in combinatory optimization [15], [16], random algorithms RANSAC [13], [17] or forward search [12].…”

Section: Introductionmentioning

confidence: 99%