Seamless, Static Multi‐Texturing of 3D Meshes

Pagés, Rafael; Berjón, Daniel; Morán, F.; García, Narciso

doi:10.1111/cgf.12508

Cited by 11 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The shape of the mesh portions of the resulting hybrid model may of course be further refined, but so may be the shape of the splat portions. And the same goes for the appearance: in particular, in our system we apply to the whole hybrid model a seamless multi-texturing technique originally conceived for 3D meshes [Pagés et al 2015] which works equally well with splats, as illustrated by Figure 1.…”

Section: Introduction: Vision and Related Workmentioning

confidence: 95%

“…Given an input point cloud obtained with a set of calibrated images (e.g., with an SfM approach, or with RGB-D sensors acquiring the 3D scene from different viewpoints), the photographs or video frames leading to that point cloud may be used to texture the resulting model. For this, we use a multi-texturing technique which manages to reduce drastically the typical inaccuracies of this kind of texture atlases (such as seams or blurs) by blending color contributions from [Pagés et al 2015]. This multi-texturing technique was originally devised for triangle meshes, but works as well with splat sets, which do not look natural when rendered with a single color each -the equivalent to flat shading in the context of mesh rendering.…”

Section: Multi-texturingmentioning

confidence: 99%

See 1 more Smart Citation

Splash

Pagés

Sánchez-García

Berjón

et al. 2015

Proceedings of the 20th International Conference on 3D Web Technology

View full text Add to dashboard Cite

We propose a hybrid 3D modeling and rendering approach called SPLASH to combine the modeling flexibility and robustness of SPLAts together with the rendering simplicity and maturity of meSHes. Together with this novel SPLASH concept, we also propose a system turning a 3D point cloud, obtained for example through an SfM (Structure from Motion) approach, into a multitextured hybrid 3D model whose shape is described by a triangle mesh plus a collection of elliptical splats.

show abstract

Section: Introduction: Vision and Related Workmentioning

confidence: 95%

Section: Multi-texturingmentioning

confidence: 99%

Splash

Pagés

Sánchez-García

Berjón

et al. 2015

Proceedings of the 20th International Conference on 3D Web Technology

View full text Add to dashboard Cite

show abstract

“…This process is based on a simplified version of the approach developed by Pagés et al [2015], which merges the color information provided by several cameras to produce a seamless textured model. Although originally designed for triangular meshes, this system works as well for splats, even when some partially occlude each other because they cover the same region of the model, and produces fine results with seamless transitions across surfaces.…”

Section: Multi-texturingmentioning

confidence: 99%

“…We therefore propose to adapt a multitexturing method originally conceived for triangular meshes [Pagés et al 2015] to increase the realism of splat-based models. In our system, several images covering the scene are blended to obtain a unique texture atlas where irregularities such as color seams or blurring are minimized, as illustrated by Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Textured splat-based point clouds for rendering in handheld devices

Sánchez-García

Pagés

Berjón

et al. 2015

Proceedings of the 20th International Conference on 3D Web Technology

View full text Add to dashboard Cite

We propose a novel technique for modeling and rendering a 3D point cloud obtained from a set of photographs of a real 3D scene as a set of textured elliptical splats. We first obtain the base splat model by calculating, for each point of the cloud, an ellipse approximating locally the underlying surface. We then refine the base model by removing redundant splats to minimize overlaps, and merging splats covering flat regions of the point cloud into larger ellipses. We later apply a multi-texturing process to generate a single texture atlas from the set of photographs, by blending information from multiple cameras for every splat. Finally, we render this multitextured, splat-based 3D model with an efficient implementation of OpenGL ES 2.0 vertex and fragment shaders which guarantees its fluid display on handheld devices.

show abstract

“…Situations in which 3D visibility occurs include stereo matching [6], object reconstruction [7,8] and motion trajectory optimization [9][10][11]. With the development of multiview-based reconstruction [12], there has been an increasing focus on texture generation of 3D surfaces [13][14][15][16][17]. Visibility checking is highly important for the smoothness and verisimilitude of textured models.…”

Section: Introductionmentioning

confidence: 99%

GPVC: Graphics Pipeline-Based Visibility Classification for Texture Reconstruction

2018

View full text Add to dashboard Cite

The shadow-mapping and ray-tracing algorithms are the two popular approaches used in visibility handling for multi-view based texture reconstruction. Visibility testing based on the two algorithms needs a user-defined bias to reduce computation error. However, a constant bias does not work for every part of a geometry. Therefore, the accuracy of the two algorithms is limited. In this paper, we propose a high-precision graphics pipeline-based visibility classification (GPVC) method without introducing a bias. The method consists of two stages. In the first stage, a shader-based rendering is designed in the fixed graphics pipeline to generate initial visibility maps (IVMs). In the second stage, two algorithms, namely, lazy-projection coverage correction (LPCC) and hierarchical iterative vertex-edge-region sampling (HIVERS), are proposed to classify visible primitives into fully visible or partially visible primitives. The proposed method can be easily implemented in the graphics pipeline to achieve parallel acceleration. With respect to efficiency, the proposed method outperforms the bias-based methods. With respect to accuracy, the proposed method can theoretically reach a value of 100%. Compared with available libraries and software, the textured model based on our method is smoother with less distortion and dislocation.

show abstract

Seamless, Static Multi‐Texturing of 3D Meshes

Abstract: Abstract

Cited by 11 publications

References 26 publications

Splash

Splash

Textured splat-based point clouds for rendering in handheld devices

GPVC: Graphics Pipeline-Based Visibility Classification for Texture Reconstruction

Contact Info

Product

Resources

About