A review of recent range image registration methods with accuracy evaluation

By Joaquim Salvi, Carles Matabosch, David Fofi, Josep Forest. Image and Vision Computing, 2007

701 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/032c5a751a646d5cf28197f8bd73a7dcfd3c0ca3

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

A Review of Point Cloud Registration Algorithms for Mobile Robotics (2015, background): “…registration in medical imagery [Maintz and Viergever, 1998, Markelj et al., 2012, Fluck et al., 2011, Pluim et al., 2003] and object reconstructions/recognition [Salvi et al., 2007, Bowyer et al., 2006], there is no scientific publication covering the evolution of registration applied to robotics.”
Accurate 3D comparison of complex topography with terrestrial laser scanner: Application to the Rangitikei canyon (N-Z) (2013, methodology): “This is not unexpected as the standard ICP works well for smooth overlapping 3D surfaces scanned at very high resolution (i.e. the corner of a room), but can have a large remaining uncertainty on noisy 2D surfaces (Salvi et al., 2007; Bae and Lichti, 2008).”
Registration of 3D Point Clouds and Meshes: A Survey from Rigid to Nonrigid (2013, background): “Among all the existing surveys (Table 1), [11]–[15] focus on rigid registration only.”
Data-driven grasping with partial sensor data (2009, background): “[30], but our problem is significantly more difficult, as we are attempting to align a partial scan of one model with the geometry of a different, neighboring model, rather than with an overlapping scan of the same model from a different viewpoint.”
Heritage Recording and 3D Modeling with Photogrammetry and 3D Scanning (2011, methodology): “The scans registration is generally done in two steps: (a) a pair-wise manual or automatic coarse alignment using targets or few homologues features and (b) final global alignment based on iterative closest points [112] or least squares method procedures [113].”
Towards 3D lidar point cloud registration improvement using optimal neighborhood knowledge (2013, methodology): “This can frequently happen in case of objects acquired with different point densities or different points of view (Salvi et al., 2007).”
Colored Point Cloud Registration Revisited (2017, neutral): “Its variants have been extensively studied [31, 33, 38].”
3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey (2014, background): “Two reviews on 3D modeling and range image registration by [30] and [31] are also worth mentioning.”
Medical image registration: a review (2014, background): “In the literature, several reviews on image registration methods can be found: overall image registration in Brown (1992), Salvi et al. (2007), Wyawahare et al. (2009), Zitova´ and Flusser (2003), medical image registration in general (Elsen et al. 1993; Maintz and Viergever 1998; Bronzino 2000;…”
Fast Global Registration (2016, neutral): “Geometric registration has been extensively studied [15, 28, 36, 38].”
DeepIM: Deep Iterative Matching for 6D Pose Estimation (2018, methodology): “The most well-known local refinement algorithm is the Iterative Closest Point (ICP) algorithm (Besl and McKay, 1992) and its variants (Rusinkiewicz and Levoy, 2001; Salvi et al., 2007; Tam et al., 2013).”