Accurate and Automatic Alignment of Range Surfaces

Fantoni, Simone; Castellani, Umberto; Fusiello, Andrea

doi:10.1109/3dimpvt.2012.63

Cited by 43 publications

(31 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This property eases the implementation and reduces errors, that are to be encountered in usual heuristics. Due to the accuracy requirements, unlike [14], we omit using distance transforms at this stage. We rather use speeded up KD-Trees to achieve exact nearest neighbors [30].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

CAD Priors for Accurate and Flexible Instance Reconstruction

Birdal

Ilić

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Close up: CAD Model Close up: Reconstruction (c) Object Detection in Laser Scans (b) Image of Object in Scene (a) CAD Model (d) 3D Reconstruction Figure 1: Our 3D reconstruction method. (a) Input 3D CAD model. (b) Image of the instance to reconstruct. (c) Detection of 3D model in point clouds. (c) Final reconstruction we obtain, with close-up comparisons to the nominal CAD prior. AbstractWe present an efficient and automatic approach for accurate instance reconstruction of big 3D objects from multiple, unorganized and unstructured point clouds, in presence of dynamic clutter and occlusions. In contrast to conventional scanning, where the background is assumed to be rather static, we aim at handling dynamic clutter where the background drastically changes during object scanning. Currently, it is tedious to solve this problem with available methods unless the object of interest is first segmented out from the rest of the scene. We address the problem by assuming the availability of a prior CAD model, roughly resembling the object to be reconstructed. This assumption almost always holds in applications such as industrial inspection or reverse engineering. With aid of this prior acting as a proxy, we propose a fully enhanced pipeline, capable of automatically detecting and segmenting the object of interest from scenes and creating a pose graph, online, with linear complexity. This allows initial scan alignment to the CAD model space, which is then refined without the CAD constraint to fully recover a high fidelity 3D reconstruction, accurate up to the sensor noise level. We also contribute a novel object detection method, local implicit shape models (LISM) and give a fast verification scheme. We evaluate our method on multiple datasets, demonstrating the ability to accurately reconstruct objects from small sizes up to 125m 3 .

show abstract

Section: Methodsmentioning

confidence: 99%

“…[28] proposed a tensor feature and a hashing framework operating on meshes. Fantoni et al [14] uses 3D keypoint matching as an initial stage of multiview alignment to bring the scans to a rough alignment. Zhu et.…”

Section: Prior Artmentioning

confidence: 99%

CAD Priors for Accurate and Flexible Instance Reconstruction

Birdal

Ilić

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…Global registration can be solved in point (correspondences) space or in frame space. In the first case, all the rigid transformations are simultaneously optimized with respect to a cost function that includes the distance between corresponding points (Pennec, 1996;Benjemaa and Schmitt, 1998;Krishnan et al, 2007;Toldo et al, 2010;Bonarrigo and Signoroni, 2011;Fantoni et al, 2012;Chaudhury et al, 2015).…”

Section: Multiple 3d Point-set Registrationmentioning

confidence: 99%

Robust synchronization in SO(3) and SE(3) via low-rank and sparse matrix decomposition

Arrigoni

Fusiello

Rossi

et al. 2018

Computer Vision and Image Understanding

Self Cite

View full text Add to dashboard Cite

This paper deals with the synchronization problem, which arises in multiple 3D point-set registration and in structure-from-motion. The problem is formulated as a low-rank and sparse matrix decomposition that caters for missing data, outliers and noise, and it benefits from a wealth of available decomposition algorithms that can be plugged-in. A minimization strategy, dubbed R-GoDec, is also proposed. Experimental results on simulated and real data show that this approach o↵ers a good trade-o↵ between resistance to outliers and speed.

show abstract

“…However, this method is computationally expensive, especially in the big data case. Guo et al [15] and Fantoni et al [16] propose approaches for the registration of point cloud data by extracting the vertex features. However, the registration failure occurs in the case that insufficient features are obtained.…”

Section: Introductionmentioning

confidence: 99%

Multi-view point cloud registration with adaptive convergence threshold and its application in 3D model retrieval

Liu

Sun

et al. 2019

Multimed Tools Appl

View full text Add to dashboard Cite

Multi-view point cloud registration is a hot topic in the communities of artificial intelligence (AI) and multimedia technology. In this paper, we propose a framework to reconstruct the 3D models by the multi-view point cloud registration algorithm with adaptive convergence threshold, and apply it to 3D model retrieval subsequently. The iterative closest point (ICP) algorithm is implemented with adaptive convergence threshold, and further combines with motion average algorithm for the registration of multi-view point cloud data. After the registration process, the applications are designed for 3D model retrieval. The geometric saliency map is computed based on the vertex curvatures. The test facial triangles are selected to compare with the standard facial triangle. The face and non-face models are then discriminated. The experiments and comparisons prove the effectiveness of the proposed framework.

show abstract

Accurate and Automatic Alignment of Range Surfaces

Cited by 43 publications

References 26 publications

CAD Priors for Accurate and Flexible Instance Reconstruction

CAD Priors for Accurate and Flexible Instance Reconstruction

Robust synchronization in SO(3) and SE(3) via low-rank and sparse matrix decomposition

Multi-view point cloud registration with adaptive convergence threshold and its application in 3D model retrieval

Contact Info

Product

Resources

About