Robust global registration

By Natasha Gelfand, Niloy J. Mitra, Leonidas J. Guibas, Helmut Pottmann. Eurographics Symposium on Geometry Processing, 2005

684 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/22069c85da6ee037eb617b8ca609d221c442d397

How researchers see this paper

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

Citations in the corpus

Fast Global Registration (2016, methodology): “Another approach to global registration is based on the branch-and-bound framework [10, 12, 18, 23, 42].”
Blended intrinsic maps (2011, background): “Even with pruning based on branch-and-bound [Gelfand et al. 2005] or priority-driven search [Funkhouser and Shilane 2006], the search space is simply too large to explore efficiently, and so heuristics are employed and/or few feature correspondences are found, which makes finding a good inter-surfac”
Contextual Part Analogies in 3D Objects (2010, background): “…focus on the need to define measures for similarity of shapes (Sundar et al. 2003; Cornea et al. 2005; Funkhouser et al. 2005), alignment of shapes (Gelfand et al. 2005) and finding complete correspondence between two models for the purposes of deformations, morphing (Alexa 2002), and…”
Partial Similarity of Objects, or How to Compare a Centaur to a Horse (2009, unknown): “Alternatively, an initialization similar to Gelfand et al. (2005) based on local shape descriptors and a branch-and-bound algorithm can be used (Raviv et al. 2007).”
Reassembling fractured objects by geometric matching (2006, methodology): “Various descriptors have been proposed including curvatures [Li and Guskov 2005; Gal and Cohen-Or 2006] and integral invariants [Gelfand et al. 2005].”
A review of multimodal image matching: Methods and applications (2021, background): “Typical points descriptors include shape context (SC) [131], spin images [304], integral volume [305], and point feature histograms [306].”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, methodology): “[48] use (Euclidean) distance-based lower bounding and branch-and-bound to reduce the correspondence search space (Section 5.”
PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet (2019, background): “For instance, scale invariant curvature descriptors [9], oriented descriptors [10], extended Gaussian images [19], fast point feature histograms [32], color intensity-based descriptors [11], global point signatures [6], heat kernels [25], etc.”
Model Composition from Interchangeable Components (2007, methodology): “Several methods do this by matching models skeletons [24, 5] or feature vertices [ 9 ].”
Go-ICP: Solving 3D Registration Efficiently and Globally Optimally (2013, background): “One exception is the work of Gelfand et al. [14] in which they proposed a globally optimal solution on top of the local descriptors.”
Learning to place new objects in a scene (2012, methodology): “ we recovered the full 3D geometry by registering the raw pointcloud against a few parameterized objects in a database using the Iterative Closest Point (ICP) algorithm (Rusinkiewicz and Levoy, 2001; Gelfand et al., 2005). Furthermore, since we had access to a full solid 3D model, we veriﬁed the sta”
Optical techniques for 3D surface reconstruction in computer-assisted laparoscopic surgery (2013, methodology): “(Bronstein et al., 2011; Funkhouser and Shilane, 2006; Gelfand et al., 2005; Lipman and Funkhouser, 2009; Wang et al., 2010; Windheuser et al., 2011; Zeng et al., 2010; Zhang et al., 2008), the only fully-automatic non-rigid approaches to intra-operative registration of range data in abdominal proce”
Scale-invariant heat kernel signatures for non-rigid shape recognition (2010, methodology): “Different approaches such as contour and edge features [30] [18], spin images [14], local patches [28] [42], conformal factor [4], differential operators [44], and local volume properties [13] were used as feature descriptors in the shape retrieval literature.”
On the Repeatability and Quality of Keypoints for Local Feature-based 3D Object Retrieval from Cluttered Scenes (2009, methodology): “Gelfand et al. (2005) compute an integral volume descriptor for each surface point and pick a sparse number of points according to the uniqueness of their descriptors.”
Towards 3D Point cloud based object maps for household environments (2008, methodology): “Furthermore, methods for generating initial approximate alignments [10,35,19], as well as choosing alternate optimization methods [14,6], improved the results of the registration process.”