Minimizing the Multi-view Stereo Reprojection Error for Triangular Surface Meshes

Delaunoy, Amaël; Prados, Emmanuel; Gargallo, Pau; Pons, Jean-Philippe; Sturm, Peter

doi:10.5244/c.22.58

Cited by 50 publications

(42 citation statements)

References 26 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All these reasons make nowadays Lagrangian methods more and more popular. Also these methods have recently proved their strong potential for 3D applications [8,20,21]. From now, we consider that the surface is a piecewise planar triangular mesh.…”

Section: Choice Of Representationmentioning

confidence: 99%

Towards Full 3D Helmholtz Stereovision Algorithms

Delaunoy

Prados

Belhumeur

2011

Computer Vision – ACCV 2010

View full text Add to dashboard Cite

Abstract. Helmholtz stereovision methods are limited to binocular stereovision or depth maps reconstruction. In this paper, we extend these methods to recover the full 3D shape of the objects of a scene from multiview Helmholtz stereopsis. Thus, we are able to reconstruct the complete three-dimensional shape of objects made of any arbitrary and unknown bidirectional reflectance distribution function. Unlike previous methods, this can be achieved using a full surface representation model. In particular occlusions (self occlusions as well as cast shadows) are easier to handle in the surface optimization process. More precisely, we use a triangular mesh representation which allows to naturally specify relationships between the geometry of a point of the scene and its surface normal. We show how to implement the presented approach using a coherent gradient descent flow. Results and benefits are illustrated on various examples.

show abstract

Section: Choice Of Representationmentioning

confidence: 99%

Towards Full 3D Helmholtz Stereovision Algorithms

Delaunoy

Prados

Belhumeur

2011

Computer Vision – ACCV 2010

View full text Add to dashboard Cite

show abstract

“…The benefits of this approach have long been recognized in mesh processing, but have seldom been demonstrated in computer vision [24][25][26]. Thus, the choice of an adequate discrete spatio-temporal representation is crucial in our work.…”

Section: Discretize Then Optimizementioning

confidence: 99%

Dense and Accurate Spatio-temporal Multi-view Stereovision

Courchay¹,

Pons²,

Monasse³

et al. 2010

Computer Vision – ACCV 2009

View full text Add to dashboard Cite

Abstract. In this paper, we propose a novel method to simultaneously and accurately estimate the 3D shape and 3D motion of a dynamic scene from multiple-viewpoint calibrated videos. We follow a variational approach in the vein of previous work on stereo reconstruction and scene flow estimation. We adopt a representation of a dynamic scene by an animated mesh, i.e. a polygonal mesh with fixed connectivity whose timevarying vertex positions sample the trajectories of material points. Interestingly, this representation ensures a consistent coding of shape and motion by construction. Our method accurately recovers 3D shape and 3D motion by optimizing the positions of the vertices of the animated mesh. This optimization is driven by an energy function which incorporates multi-view and inter-frame photo-consistency, smoothness of the spatio-temporal surface and of the velocity field. Central to our work is an image-based photo-consistency score which can be efficiently computed and which fully handles projective distortion and partial occlusions. We demonstrate the effectiveness of our method on several challenging realworld dynamic scenes.

show abstract

“…We then developed it for the case of discrete surface representations, in particular triangular meshes [2] which in practice allow to achieve a higher 3D surface resolution. Also, even when using a continuous setup, in practice the surface representation is finally discretized and the surface evolution requires to repeatedly discretize attributes.…”

Section: Overviewmentioning

confidence: 99%

3D and Appearance Modeling from Images

Sturm

Delaunoy

Gargallo

et al. 2009

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. This paper gives an overview of works done in our group on 3D and appearance modeling of objects, from images. The backbone of our approach is to use what we consider as the principled optimization criterion for this problem: to maximize photoconsistency between input images and images rendered from the estimated surface geometry and appearance. In initial works, we have derived a general solution for this, showing how to write the gradient for this cost function (a non-trivial undertaking). In subsequent works, we have applied this solution to various scenarios: recovery of textured or uniform Lambertian or non-Lambertian surfaces, under static or varying illumination and with static or varying viewpoint. Our approach can be applied to these different cases, which is possible since it naturally merges cues that are often considered separately: stereo information, shading, silhouettes. This merge naturally happens as a result of the cost function used: when rendering estimated geometry and appearance (given known lighting conditions), the resulting images automatically contain these cues and their comparison with the input images thus implicitly uses these cues simultaneously. OverviewImage-based 3D and appearance modeling is a vast area of investigation in computer vision and related disciplines. A recent survey of multi-view stereo methods is given in [6]. In this invited paper, we provide a brief overview of a set of works done in our group, mainly by showing sample results. Technical details can be found in the relevant cited publications.3D and appearance modeling from images, like so many estimation problems, is usually formulated, explicitly or implicitly, as a (non-linear) optimization problem 1 . One of the main questions is of course which criterion to optimize. We believe that the natural criterion is to maximize photoconsistency between input images and images rendered from the estimated surface geometry and appearance (to be precise, this criterion corresponds to the likelihood term of a Bayesian problem formulation, which can be combined with suitable priors). To measure 1 There exist some exceptions in special cases. For example, in basic shape-fromsilhouettes, the 3D shape is directly defined by the input and no estimation is necessary, just a computation to explicitly retrieve the shape.E.

show abstract

Minimizing the Multi-view Stereo Reprojection Error for Triangular Surface Meshes

Cited by 50 publications

References 26 publications

Towards Full 3D Helmholtz Stereovision Algorithms

Towards Full 3D Helmholtz Stereovision Algorithms

Dense and Accurate Spatio-temporal Multi-view Stereovision

3D and Appearance Modeling from Images

Contact Info

Product

Resources

About