Unsupervised texture reconstruction method using bidirectional similarity function for 3-D measurements

Wu, Juanjuan; Chen, Hailong; Liu, Xiaoli; Cao, Liangcai; Peng, Xiang; Jin, Guofan

doi:10.1016/j.optcom.2019.01.051

Cited by 8 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, some researchers have adopted matching learning approaches to recovering textured models. For example, Wu et al 31 proposed to use an unsupervised learning approach to texture reconstruction, in which they also use a bidirectional similarity function for 3‐D measurements, and a composite weight texture blending method is presented to release the artifacts caused by texture misalignment and inconsistent illumination. Kelly et al 15 proposed an automatic data fusion method for large‐scale structured urban reconstruction, in which the authors designed a binary integer scheme that globally balances sources of error to produce semantically parsed surface models with corresponding façade elements.…”

Section: Related Workmentioning

confidence: 99%

Parallel surface reconstruction for large‐scale scenes in the wild

Cao

Gao

Jia

2021

Circuit Theory & Apps

View full text Add to dashboard Cite

Recovering a high‐quality texture model in a short time still a pursued goal in both computer vision and graphics communities. Thus, in the past decade, several methods have been proposed for fitting a texture model from the dense point clouds. However, these methods are computational intensity and also suffer from noise especially in outdoor. Moreover, with the popularization of Unmanned Aerial Vehicles (UAVs), it is getting easier to capture image data. While modern methods have much novelty, they may spend a long time on big image datasets. To accelerate the process of texture modeling, in this paper we present a parallel approach to fitting a texture model from the dense point clouds. The presented method makes use of the parallel computing technology and is implemented in parallel octree structure as well as parallel marching cubes. Finally, we conduct a comprehensive experiment on several benchmarking datasets and experimental results show that our method outperforms the state‐of‐the‐art methods and has also a 20 times acceleration.

show abstract

Section: Related Workmentioning

confidence: 99%

Parallel surface reconstruction for large‐scale scenes in the wild

Cao

Gao

Jia

2021

Circuit Theory & Apps

View full text Add to dashboard Cite

show abstract

“…In (W. , (Kim et al, 2019), (Fu et al, 2018), and (Rouhani et al, 2018), texture optimization techniques have been adopted to improve the quality of the final texture, reducing ghosting and blurring problems. More recently, Deep Learning techniques have been adopted (Huang et al, 2020), (Richard et al, 2020), (Y. , and (Wu et al, 2019), with which results outperform the quality of previous methods.…”

Section: Techniques For Texture Enhancementmentioning

confidence: 99%

3D Reconstruction and Texture Refinement with Image Enhancement for Improved Visual Quality

Corona-Patricio¹,

Reta²

2021

EJT

View full text Add to dashboard Cite

This paper proposes a method to generate surface and texture models from rigid objects captured with an RGB-D camera. The method integrates five stages: 1. Point cloud generation from RGB-D images; 2. Surface model generation; 3. Surface model refinement; 4. Texture generation and mapping; 5. Texture enhancement. The use of image processing algorithms for texture enhancement and the refinement of the surface models enables the improvement of the appearance of reconstructed models. The performed experimentation shows the results of the proposed method for five small textured objects. The appearance of reconstructed models was evaluated using a visual quality index; a sharper texture helps to improve such index.

show abstract

“…However, within the framework of 3D computer graphics, use of the BRDF does not resolve the problem because it does not capture the spatial structure of textured materials. For this reason, the BRDF concept has been extended to a more generic definition of bidirectional texture function (BTF), which aims to capture all the variations of textured materials, including non‐local effects in rough material structures such as occlusions, masking, subsurface spreading and inter‐reflections 6,7 …”

Section: Measurement Of Optical Properties Related To Colour Appearancementioning

confidence: 99%

“…For this reason, the BRDF concept has been extended to a more generic definition of bidirectional texture function (BTF), which aims to capture all the variations of textured materials, including non-local effects in rough material structures such as occlusions, masking, subsurface spreading and inter-reflections. 6,7 A monospectral BTF is a six-dimensional function BTF…”

Section: Properties Related To Colour Appearancementioning

confidence: 99%

Colour appearance in immersive three‐dimensional virtual environments

Díaz‐Barrancas

Cwierz

Pardo

et al. 2020

Coloration Technology

View full text Add to dashboard Cite

Technology is constantly evolving and, consequently, all the technological advances taking place are regularly integrated into the daily life of society. During recent years, there has been a trend towards virtual resources such as teleworking, telemedicine and e-commerce. In many countries, this virtualisation process has been accelerated by the changing circumstances caused by the COVID-19 pandemic. In any case, there is a growing demand for virtual systems, and virtual reality is a suitable field for the application of a multitude of solutions. However, advances in virtual reality occur without any regard to colour science, and there are several challenges to be overcome to improve the visual appearance and fidelity of colour reproduction in all types of related devices. This paper discusses three open issues related to the visual appearance and visual fidelity of virtual reality systems. We believe it is necessary to direct future research efforts in each of these directions to secure improvements in the visual fidelity of virtual reality systems.

show abstract

Unsupervised texture reconstruction method using bidirectional similarity function for 3-D measurements

Cited by 8 publications

References 23 publications

Parallel surface reconstruction for large‐scale scenes in the wild

Parallel surface reconstruction for large‐scale scenes in the wild

3D Reconstruction and Texture Refinement with Image Enhancement for Improved Visual Quality

Colour appearance in immersive three‐dimensional virtual environments

Contact Info

Product

Resources

About