Locally rigid globally non-rigid surface registration

Fujiwara, Kent; Nishino, Ko; Takamatsu, Jun; Zheng, Bo; Ikeuchi, Katsushi

doi:10.1109/iccv.2011.6126411

Cited by 27 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these algorithms, like RANSAC, require an a priori parametric model of the transformation whose parameters are computed using the correspondences, and thus, difficult to generalise to arbitrary deformations. Similar limitations are also shared by methods relying on implicit shape models [14], [24]. In the Gaussian Process framework we propose, we also progressively reduce the number of potential correspondences but, in contrast to previous approaches, no a priori parametric deformation model is required.…”

Section: Related Workmentioning

confidence: 90%

Non-Rigid Graph Registration Using Active Testing Search

Serradell

Pinheiro

Sznitman

et al. 2015

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

Abstract-We present a new approach for matching sets of branching curvilinear structures that form graphs embedded in R 2 or R 3 and may be subject to deformations. Unlike earlier methods, ours does not rely on local appearance similarity nor does require a good initial alignment. Furthermore, it can cope with non-linear deformations, topological differences, and partial graphs. To handle arbitrary non-linear deformations, we use Gaussian Processes to represent the geometrical mapping relating the two graphs. In the absence of appearance information, we iteratively establish correspondences between points, update the mapping accordingly, and use it to estimate where to find the most likely correspondences that will be used in the next step. To make the computation tractable for large graphs, the set of new potential matches considered at each iteration is not selected at random as in many RANSAC-based algorithms. Instead, we introduce a so-called Active Testing Search strategy that performs a priority search to favor the most likely matches and speed-up the process. We demonstrate the effectiveness of our approach first on synthetic cases and then on angiography data, retinal fundus images, and microscopy image stacks acquired at very different resolutions.

show abstract

Section: Related Workmentioning

confidence: 90%

Non-Rigid Graph Registration Using Active Testing Search

Serradell

Pinheiro

Sznitman

et al. 2015

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…However, these algorithms, like RANSAC, require an a priori parametric model whose parameters are computed using the correspondences, and thus, cannot generalize to arbitrary deformations. Similar limitations are also shared by methods relying on implicit shape models [17,8]. In the Gaussian Process framework we propose, we also progressively reduce the number of potential correspondences but, in contrast to these previous approaches, no parametric deformation model is required.…”

Section: Related Workmentioning

confidence: 90%

Robust non-rigid registration of 2D and 3D graphs

Serradell

Głowacki²,

Kybic³

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…The energy function is described by two terms: the data term E Data (W t−1 , S, T ) is a non-rigid ICP function (N-ICP), measuring the difference between the model and the live frame. As non-rigid registration in R 3 is an inherently ill-posed problem [14], an infinite number of solutions can be found, with no guarantee of consistency between frames. To address this issue, an As-Rigid-As-Possible (ARAP) [38] regularisation term E Reg (W t−1 , S) was introduced.…”

Section: Reconstructionmentioning

confidence: 99%

FullFusion: A Framework for Semantic Reconstruction of Dynamic Scenes

Bujanca

Luján

Lennox

2019

2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)

View full text Add to dashboard Cite

Assuming that scenes are static is common in SLAM research. However, the world is complex, dynamic, and features interactive agents. Mobile robots operating in a variety of environments in real-life scenarios require an advanced level of understanding of their surroundings. Therefore, it is crucial to find effective ways of representing the world in its dynamic complexity, beyond the geometry of static scene elements. We present a framework that enables incremental reconstruction of semantically-annotated 3D models in dynamic settings using commodity RGB-D sensors. Our method is the first to perform semantic reconstruction of non-rigidly deforming objects along with a static background. FullFusion is a step towards enabling robots to have a deeper and richer understanding of their surroundings, and can facilitate the study of interaction and scene dynamics. To showcase the potential of FullFusion, we provide a quantitative and qualitative evaluation on a baseline implementation which employs specific reconstruction and segmentation pipelines. It is, however, important to highlight that the modular design of the framework allows us to easily replace any of the components with new or existing counterparts.

show abstract

Locally rigid globally non-rigid surface registration

Cited by 27 publications

References 18 publications

Non-Rigid Graph Registration Using Active Testing Search

Non-Rigid Graph Registration Using Active Testing Search

Robust non-rigid registration of 2D and 3D graphs

FullFusion: A Framework for Semantic Reconstruction of Dynamic Scenes

Contact Info

Product

Resources

About