Search

Since a few years, structure-from-motion and multi-view stereo pipelines have become omnipresent in the cultural heritage domain. The fact that such Image-Based Modelling (IBM) approaches are capable of providing a photo-realistic texture along the threedimensional (3D) digital surface geometry is often considered a unique selling point, certainly for those cases that aim for a visually pleasing result. However, this texture can very often also obscure the underlying geometrical details of the surface, making it very hard to assess the morphological features of the digitised artefact or scene. Instead of constantly switching between the textured and untextured version of the 3D surface model, this paper presents a new method to generate a morphology-enhanced colour texture for the 3D polymesh. The presented approach tries to overcome this switching between objects visualisations by fusing the original colour texture data with a specific depiction of the surface normals. Whether applied to the original 3D surface model or a lowresolution derivative, this newly generated texture does not solely convey the colours in a proper way but also enhances the smalland large-scale spatial and morphological features that are hard or impossible to perceive in the original textured model. In addition, the technique is very useful for low-end 3D viewers, since no additional memory and computing capacity are needed to convey relief details properly. Apart from simple visualisation purposes, the textured 3D models are now also better suited for on-surface interpretative mapping and the generation of line drawings.

Two important visual properties of paintings and painting-like images are the absence of texture details and the increased sharpness of edges as compared to photographic images. Painting-like artistic effects can be achieved from photographic images by filters that smooth out texture details, while preserving or enhancing edges and corners. However, not all edge preserving smoothers are suitable for this purpose. We present a simple nonlinear local operator that generalizes both the well known Kuwahara filter and the more general class of filters known in the literature as ldquocriterion and value filter structure.rdquo This class of operators suffers from intrinsic theoretical limitations which give rise to a dramatic instability in presence of noise, especially on shadowed areas. Such limitations are discussed in the paper and overcome by the proposed operator. A large variety of experimental results shows that the output of the proposed operator is visually similar to a painting. Comparisons with existing techniques on a large set of natural images highlight conditions on which traditional edge preserving smoothers fail, whereas our approach produces good results. In particular, unlike many other well established approaches, the proposed operator is robust to degradations of the input image such as blurring and noise contamination.

Disparity estimation has been investigated for decades. Fully automatic methods have problems in texture-less regions, around object boundaries and in occlusions regions. In this paper, we exploit user input to address these problematic areas interactively. By drawing contours and polygons, we achieve sharp disparity discontinuities and smooth disparity planes in the disparity maps. Annotations are tracked quite accurately over a number of frames. Experimental results on Middlebury data set and our own stereo video suggest that the accuracy of disparity maps can be improved significantly with limited user input.

Texture mapping has long been used in computer graphics to \ud enhance the realism of virtual scenes. However, to match the 3D model feature points with the corresponding pixels in a texture image, surface parameterization must satisfy specific positional constraints. However, despite numerous \ud research efforts, the construction of a mathematically robust, foldover‐free parameterization that is subject to \ud positional constraints continues to be a challenge. In the \ud present paper, this foldover problem is addressed by developing radial basis function (RBF) based reparameterization. Given initial 2D embedding of a 3D \ud surface, the proposed method can reparameterize 2D embedding into a foldover ‐free 2D mesh, satisfying a set \ud of user‐specified constraint points. In addition, this approach is mesh‐free. Therefore, generating smooth texture \ud mapping results is possible without extra smoothing optimization.

In augmented reality, marker-based tracking is the most common method for camera pose estimation. Most of the markers are black and white patterns that are visually obtrusive, but they can be hidden from the video using image inpainting methods. In this paper, we present a computationally efficient approach to achieve this. We use a high-resolution hiding texture, which is captured and generated only once. To capture continuous changes in illumination, reflections and exposure, we also compute a very low-resolution texture at each frame. The coarse and fine textures are combined to obtain a detailed hiding texture which reacts to changing conditions and runs efficiently in mobile phone environments.

In this paper, we present a novel method for texture mapping of closed surfaces. Our method is based on the technique of optimal mass transport (also known as the ?earth-mover's metric?). This is a classical problem that concerns determining the optimal way, in the sense of minimal transportation cost, of moving a pile of soil from one site to another. In our context, the resulting mapping is area preserving and minimizes angle distortion in the optimal mass sense. Indeed, we first begin with an angle-preserving mapping (which may greatly distort area) and then correct it using the mass transport procedure derived via a certain gradient flow. In order to obtain fast convergence to the optimal mapping, we incorporate a multiresolution scheme into our flow. We also use ideas from discrete exterior calculus in our computations.

In this paper, we present a new method for bidirectional relighting for 3D-aided 2D face recognition under large pose and illumination changes. During subject enrollment, we build subject-specific 3D annotated models by using the subjects' raw 3D data and 2D texture. During authentication, the probe 2D images are projected onto a normalized image space using the subject-specific 3D model in the gallery. Then, a bidirectional relighting algorithm and two similarity metrics (a view-dependent complex wavelet structural similarity and a global similarity) are employed to compare the gallery and probe. We tested our algorithms on the UHDB11 and UHDB12 databases that contain 3D data with probe images under large lighting and pose variations. The experimental results show the robustness of our approach in recognizing faces in difficult situations.

A shell map (Porumbescu et al., 2005) is a bijective mapping between shell space (the space between a base surface and its offset) and texture space. It can be used to generate small-scale features on surfaces using a variety of modeling techniques. In this paper, we present an efficient algorithm, which reduces distortion by construction, for the offset surface generation of triangular meshes. The basic idea is to independently offset each triangle of the base mesh, and then stitch them up by solving a Poisson equation. We then introduce the details for computation of a stretch metric, which measures the distortion of shell maps. Our results show a substantial improvement compared to previous results.

This paper deals with the problem of badly posed image classification. Although underestimated in practice, bad-posedness is likely to affect many real-world image classification tasks, where reference samples are difficult to collect (e.g., in remote sensing (RS) image mapping) and/or spatial autocorrelation is relevant. In an image classification context affected by a lack of reference samples, an original inductive learning multiscale image classifier, termed multiscale semisupervised expectation maximization (MSEM), is proposed. The rationale behind MSEM is to combine useful complementary properties of two alternative data mapping procedures recently published outside of image processing literature, namely, the multiscale modified Pappas adaptive clustering (MPAC) algorithm and the sample-based semisupervised expectation maximization (SEM) classifier. To demonstrate its potential utility, MSEM is compared against nonstandard classifiers, such as MPAC, SEM and the single-scale contextual SEM (CSEM) classifier, besides against well-known standard classifiers in two RS image classification problems featuring few reference samples and modestly useful texture information. These experiments yield weak (subjective) but numerous quantitative map quality indexes that are consistent with both theoretical considerations and qualitative evaluations by expert photointerpreters. According to these quantitative results, MSEM is competitive in terms of overall image mapping performance at the cost of a computational overhead three to six times superior to that of its most interesting rival, SEM. More in general, our experiments confirm that, even if they rely on heavy class-conditional normal distribution assumptions that may not be true in many real-world problems (e.g., in highly textured images), semisupervised classifiers based on the iterative expectation maximization Gaussian mixture model solution can be very powerful in practice when: 1) there is a lack of reference samples with respect to the problem/model complexity and 2) texture information is considered negligible (i.e., a piecewise constant image model holds).

Subsurface scattering within translucent objects is a complex phenomenon. Designing and rendering this kind of material requires a faithful description of their aspects as well as a realistic simulation of their interaction with light. This paper presents an efficient rendering technique of multilayered translucent objects. We present a new method for modeling and rendering such complex organic materials made up of multiple layers of variable thickness. Based on the relief texture mapping algorithm, our method calculates the single scattering contribution for this kind of material in real-time using commodity graphics hardware. Our approach needs the calculation of distances traversed by a light ray through a translucent object. This calculation is required for evaluating the attenuation of light within the material. We use a surface approximation algorithm to quickly evaluate these distances. Our whole algorithm is implemented using pixel shaders. \\ La diffusion de la lumière l'intérieur de matériaux participants est un phénomène complexe. Pour modéliser et rendre de tels matériaux, il est nécessaire d'avoir une description adaptée de ceux-ci ainsi qu'une simulation réaliste de leurs interactions avec la lumière. Ce papier présente une technique de rendu adaptée aux matériaux multicouches. Cette nouvelle méthode permet de modéliser des matériaux organiques complexes composés de couches multiples à épaisseur variable. Basée sur l'algorithme du relief mapping, notre méthode permet le calcul temps réel de la diffusion simple pour ce type de matériau, et ce en exploitant les performances des cartes graphiques. Notre méthode nécessite le calcul des distances parcourues par la lumière l'intérieur des diffrentes couches du matériau. Ce calcul est nécessaire pour l'évaluation de l'atténuation de la lumière l'intérieur du matériau. Nous proposons d'utiliser un algorithme d'approximation de surface pour raliser ce calcul rapidement. Notre algorithme est implementé à l'aide de pixel shader.

International audience; This paper presents a novel image-based approach to render plausible soft shadows for complex dynamic scenes with rectangular light sources. The algorithm's performance is mostly independent of the scene complexity and the source's size. Occluders and receivers do not need to be separated and no knowledge about the scene representation is required, making the method easy to use. The main idea is to approximate the occlusion in the scene with pre- filtered occlusion textures. The visibility of the light source at a point in space is estimated by accumulating the occlusion caused by each texture, using a novel formula based on probabilities.

This paper presents a new approach to rotation invariant texture classification. The proposed approach benefits from the fact that most of the texture patterns either have directionality (anisotropic textures) or are not with a specific direction (isotropic textures). The wavelet energy features of the directional textures change significantly when the image is rotated. However, for the isotropic images, the wavelet features are not sensitive to rotation. Therefore, for the directional textures, it is essential to calculate the wavelet features along a specific direction. In the proposed approach, the Radon transform is first employed to detect the principal direction of the texture. Then, the texture is rotated to place its principal direction at 0 degrees. A wavelet transform is applied to the rotated image to extract texture features. This approach provides a features space with small intraclass variability and, therefore, good separation between different classes. The performance of the method is evaluated using three texture sets. Experimental results show the superiority of the proposed approach compared with some existing methods.

International audience; This paper presents a framework for modeling, animating and morphing textured implicit models. Our hierarchical skeletal implicit surface model incorporates key-frame animation and procedural solid texturing in a unified and coherent way. Our system enables the designer to create complex special effects by synchronizing shape, animation and texture transformations.

In this paper we propose a new method for the creation of normal maps for recovering the detail on simplified meshes and a set of objective techniques to metrically evaluate the quality of different recovering techniques. The proposed techniques, that automatically produces a normal-map texture for a simple 3D model that "imitates" the high frequency detail originally present in a second, much higher resolution one, is based on the computation of per-texel visibility and self-occlusion information. This information is used to define a point-to-point correspondence between simplified and hires meshes. Moreover, we introduce a number of criteria for measuring the quality (visual or otherwise) of a given mapping method, and provide efficient algorithms to implement them. Lastly, we apply them to rate different mapping methods, including the widely used ones and the new one proposed here.