2017
DOI: 10.1007/978-3-319-68560-1_46
|View full text |Cite
|
Sign up to set email alerts
|

Dynamic 3D Scene Reconstruction and Enhancement

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
5

Relationship

3
2

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 26 publications
0
3
0
Order By: Relevance
“…The static map produced by our framework is of highly better quality because our framework is robust to light changes, occlusions, slow or very fast motions, etc. Getting the clustered motion trajectories, the 3D reconstruction of moving objects can be obtained by registering the sparse point clouds from different view ports during their motions, see our previous works [46,47].…”
Section: Static Map and Rigid Object Reconstructionmentioning
confidence: 99%
“…The static map produced by our framework is of highly better quality because our framework is robust to light changes, occlusions, slow or very fast motions, etc. Getting the clustered motion trajectories, the 3D reconstruction of moving objects can be obtained by registering the sparse point clouds from different view ports during their motions, see our previous works [46,47].…”
Section: Static Map and Rigid Object Reconstructionmentioning
confidence: 99%
“…The 3-point RANSAC algorithm uses Cayley representation of the rotation matrix, which allows to obtain rigid transformation between point clouds using linear solvers, similar to [6]. In addition, an Iterative Closest Point algorithm [7] is applied to refine the registration. Finally, the reconstruction of the moving objects is also obtained, in a very similar manner -by registering their observations from different view-ports.…”
Section: Static-map and Dynamic Object Reconstructionmentioning
confidence: 99%
“…Therefore, such reconstruction suffers from several visual artefacts due to the dynamic parts. In this regard, recent work by Jiang et al [4][5][6] categorizes the scene into static and dynamic parts before performing VO. Their method focuses on improving VO measurements, and the attempted dynamic object reconstruction is rather preliminary and naive.…”
Section: Introductionmentioning
confidence: 99%