Description of Complex Objects from Multiple Range Images Using an Inflating Balloon Model

Chen, Yang; Medioni, Gérard

doi:10.1006/cviu.1995.1026

Cited by 57 publications

(34 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Algorithms in the third category, called surface fitting methods, approach the reconstruction problem by deforming a base-model to optimally fit the input sample points [Terzopoulos andVasilescu, 1991, Chen andMedioni, 1995]. These approaches represent the base-shape as a collection of points with springs between them and adapt the shape by adjusting either the spring stiffnesses or the point positions as a function of the surface information.…”

Section: Surface Reconstructionmentioning

confidence: 99%

Automatic reconstruction of textured 3D models

Pitzer

Kammel

DuHadway

et al. 2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract3D reconstruction and visualization of environments is increasingly important and there is a wide range of application areas where 3D models are required. Reconstructing 3D models has therefore been a major research focus in academia and industry. For example, large scale efforts for the reconstruction of city models at a global scale are currently underway. A major limitation in those efforts is that creating realistic 3D models of environments is a tedious and time consuming task. In particular, two major issues persist which prevent a broader adoption of 3D modeling techniques: a lack of affordable 3D scanning devices that enable an easy acquisition of 3D data and algorithms capable of automatically processing this data into 3D models. We believe that autonomous technologies, which are capable of generating textured 3D models of real environments, will make the modeling process affordable and enable a wide variety of new applications. This thesis addresses the problem of automatic 3D reconstruction and we present a system for unsupervised reconstruction of textured 3D models in the context of modeling indoor environments. The contributions are solutions to all aspects of the modeling process and an integrated system for the automatic creation of large scale 3D models. We first present a robotic data acquisition system which allows us to automatically scan large environments in a short amount of time. We also propose a calibration procedure for this system that determines the internal and external calibration which is necessary to transform data from one sensor into the coordinate system of another sensor. Next, we present solutions for the multi-view data registration problem, which is essentially the problem of aligning the data of multiple 3D scans into a common coordinate system. We propose a novel nonrigid registration method based on a probabilistic SLAM framework. This method incorporates spatial correlation models as map priors to guide the optimization. Scans are aligned by optimizing robot pose estimates as well as scan points. We show that this non-rigid registration significantly improves the alignment. Next, we address the problem of reconstructing a consistent 3D surface representation from the registered point clouds. We propose a volumetric surface reconstruction method based on a Poisson framework. In a second step, we improve the accuracy of this reconstruction by optimizing the mesh vertices to achieve a better approximation of the true surface. We demonstrate that this method is very suitable for the reconstruction of indoor environments. Finally, we present a solution to the reconstruction of texture maps from multiple scans. Our texture reconstruction approach partitions the surface into segments, unfolds each segment onto a plane, and reconstructs a texture map by blending multiple views into a single composite. This technique results in a very realistic reconstruction of the surface appearance and greatly enhances the visual impression by adding more realism.

show abstract

Section: Surface Reconstructionmentioning

confidence: 99%

Automatic reconstruction of textured 3D models

Pitzer

Kammel

DuHadway

et al. 2010

2010 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

show abstract

“…Recently the eld of imagebased rendering has matured su ciently to provide some competition to the model-based paradigm. The idea is to not create a geometric model, but instead to use the images directly, and therefore bypass the model creation step 42,43,44].…”

Section: Image-based Versus Model-based Technologymentioning

confidence: 99%

Building Models from Sensor Data: An Application Shared by the Computer Vision and the Computer Graphics Community

Roth¹

2000

Confluence of Computer Vision and Computer Graphics

View full text Add to dashboard Cite

“…There are two main approaches: to model painting as use, available at https://www.cambridge.org/core/terms. https://doi.org/10.1017/S144618110001169X [3] Aesthetic factors in geometric modelling 171 a physical process or to simulate the effects of the painting process. The modelling in most cases has been carried out for both the geometric shape and the shade (or colour) of a brush stroke.…”

Section: D Creative Activitiesmentioning

confidence: 99%

“…There exist a number of dynamic (or deformable) models which are designed to capture the dynamic nature of a malleable surface and yet retain surface discontinuities (see for example [3,5,22]). These techniques obtain a surface description in terms of triangular meshes from a set of 3D data which may come from various sources such as range data or contours.…”

Section: Deformable Object Representationsmentioning

confidence: 99%

Aesthetic factors in geometric modelling

Pham

2000

ANZIAM J.

View full text Add to dashboard Cite

CAD systems have traditionally catered for architectural and mechanical engineering designs which are somewhat constrained in scope. Problems concerning other types of design such as art design, industrial design or sculpting, where creativity and aesthetic factors play an important role, are not adequately addressed. These types of design require much more flexibility in both geometric modelling capability and user-machine interaction. This paper first gives a brief overview of recent work which deals with creative activities, and analyses important issues that need to be addressed in object representations for 3D creative activities. We then discuss a scheme to categorise and represent aesthetic factors in geometric modelling.

show abstract

Description of Complex Objects from Multiple Range Images Using an Inflating Balloon Model

Cited by 57 publications

References 12 publications

Automatic reconstruction of textured 3D models

Automatic reconstruction of textured 3D models

Building Models from Sensor Data: An Application Shared by the Computer Vision and the Computer Graphics Community

Aesthetic factors in geometric modelling

Contact Info

Product

Resources

About