Implicit Meshes for Effective Silhouette Handling

Ilić, Slobodan; Salzmann, Mathieu; Fua, Pascal

doi:10.1007/s11263-006-8595-0

Cited by 23 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ilic et al [7] uses an implicit representation of 3D shapes. Occluding contours are computed as the solution of an ordinary differential equation.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Direct Estimation of Non-Rigid Registrations with Image-Based Self-Occlusion Reasoning

Gripon

Bartoli²,

Sayd

2007

2007 IEEE 11th International Conference on Computer Vision

View full text Add to dashboard Cite

The registration problem for images of a deforming surface has been well studied. External occlusions are usually well-handled. In 2D image-based registration, selfocclusions are more challenging. Consequently, the surface is usually assumed to be only slightly self-occluding.This paper is about image-based non-rigid registration with self-occlusion reasoning. A specific framework explicitly modeling self-occlusions is proposed. It is combined with an intensity-based, i.e. direct, data term for registration. Self-occlusions are detected as shrinking areas in the 2D warp.Experimental results on several challenging datasets show that our approach successfully registers images with self-occlusions while effectively detecting the occluded regions.

show abstract

“…Ilic et al [7] uses an implicit representation of 3D shapes. Occluding contours are computed as the solution of an ordinary differential equation.…”

Section: Previous Workmentioning

confidence: 99%

“…Deformation estimation in the presence of self-occlusions could be formulated in 3D, see e.g. [7]. However, recovering a 3D surface, its deformations and the camera pose from a monocular video sequence is intrinsically ill-posed.…”

Section: Introductionmentioning

confidence: 99%

Direct Estimation of Non-Rigid Registrations with Image-Based Self-Occlusion Reasoning

Gripon

Bartoli²,

Sayd

2007

2007 IEEE 11th International Conference on Computer Vision

View full text Add to dashboard Cite

show abstract

“…The most commonly used simulation techniques are mesh-based methods such as Finite Element Method (FEM) [10], [11], [12], mass-spring [13] and boundary element method (BEM) [14], [15]. FEM is able to model the deformation with high physical accuracy but it is computationally expensive and complex, which makes it unsuitable for many time-critical applications [5].…”

Section: Related Workmentioning

confidence: 99%

Estimating the deformability of elastic materials using optical flow and position-based dynamics

Giiler

Pauwels

Pieropan

et al. 2015

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

Abstract-Knowledge of the physical properties of objects is essential in a wide range of robotic manipulation scenarios. A robot may not always be aware of such properties prior to interaction. If an object is incorrectly assumed to be rigid, it may exhibit unpredictable behavior when grasped. In this paper, we use vision based observation of the behavior of an object a robot is interacting with and use it as the basis for estimation of its elastic deformability. This is estimated in a local region around the interaction point using a physics simulator. We use optical flow to estimate the parameters of a position-based dynamics simulation using meshless shape matching (MSM). MSM has been widely used in computer graphics due to its computational efficiency, which is also important for closed-loop control in robotics. In a controlled experiment we demonstrate that our method can qualitatively estimate the physical properties of objects with different degrees of deformability.

show abstract

“…In order to overcome this problem, several modeling methods based on occluding contours have been proposed [9,10,6,5,4]. Although occluding contours are useful for free-form object localization, there are some pose which cannot be uniquely localized using only occluding contours [10].…”

Section: Introductionmentioning

confidence: 99%

3D Contour Model Creation for Stereo-Vision Systems

Maruyama

Kawai

Tomita

2010

2010 20th International Conference on Pattern Recognition

View full text Add to dashboard Cite

The present paper describes a method for automatic 3D contour model creation for stereo-vision systems. The object model is a triangular surface mesh and a set of aspect models, which consists of model features and model points. Model features and model points are generated using 3D contours, which are estimated by the projected images of the triangular surface mesh from multiple discrete viewing directions. Using a nonphotorealistic rendering approach, we extract not only the outer contours but also the inner contours of the projected images. Using both the inner and outer contours of the projected images, we create the object model which has 3D inner contour features and 3D contour generator features. Experimental results obtained using the 3D localization algorithm demonstrate the effectiveness of the proposed model.

show abstract

Implicit Meshes for Effective Silhouette Handling

Cited by 23 publications

References 37 publications

Direct Estimation of Non-Rigid Registrations with Image-Based Self-Occlusion Reasoning

Direct Estimation of Non-Rigid Registrations with Image-Based Self-Occlusion Reasoning

Estimating the deformability of elastic materials using optical flow and position-based dynamics

3D Contour Model Creation for Stereo-Vision Systems

Contact Info

Product

Resources

About