Article
Chemistry, Analytical
Jaime Maldonado, Lino Antoni Giefer
Summary: The study systematically evaluated the saliency maps computed with four selected bottom-up models on images of urban and highway traffic scenes, identifying significant differences in salient areas. The findings provide insights for prospective applications in autonomous driving, such as object detection and tracking.
Article
Computer Science, Artificial Intelligence
Xiaoying Ding, Zhenzhong Chen
Summary: In this work, a novel 6DoF mesh saliency database is developed, providing both the subject's 6DoF data and eye-movement data. The inter-observer variation, influence of viewing direction, visual attention bias, and head movement during observation are analyzed based on the database. A 6DoF mesh saliency detection algorithm is proposed, taking into consideration uniqueness measure and bias preference. The experimental results demonstrate the superior performance of the approach, providing benchmarks for the presented 6DoF mesh saliency database.
Article
Geography, Physical
Minglei Li, Liangliang Nan
Summary: This paper presents a method for filtering and simplifying 3D building mesh models that can preserve piecewise planar structures and sharp features while reducing the number of faces effectively. By using edge collapse operations and regional structural constraints, the method is able to simplify building meshes while maintaining meaningful levels of detail.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Computer Science, Software Engineering
Hsueh-Ti Derek Liu, Mark Gillespie, Benjamin Chislett, Nicholas Sharp, Alec Jacobson, Keenan Crane
Summary: This paper presents a fast method for simplifying surface meshes by constructing a coarse intrinsic triangulation of the input domain and using greedy decimation based on the quadric error metric. Instead of storing extrinsic quadrics, intrinsic tangent vectors are used to track curvature drift during simplification. The method provides a black box approach to geometry processing, allowing mesh resolution to be decoupled from the matrix size used for solving equations, and it benefits fundamental tasks such as geometric multigrid, geodesic distance computation, mean curvature flow, geodesic Voronoi diagrams, and the discrete exponential map.
ACM TRANSACTIONS ON GRAPHICS
(2023)
Article
Mathematics, Interdisciplinary Applications
Yufei Guo, Chuanrui Wang, Zhe Ma, Xuhui Huang, Kewu Sun, Rongli Zhao
Summary: A new mesh smoothing method is proposed in this paper, combining the advantages of heuristic smoothing and optimization-based smoothing, which is more efficient and effective in improving mesh quality compared to traditional methods.
COMPUTATIONAL MECHANICS
(2022)
Article
Multidisciplinary Sciences
Mohamed H. Mousa, Mohamed K. Hussein
Summary: Advances in high-performance computing technologies have significantly improved computer graphics techniques, especially those related to mesh simplification. Recent progress in GPUs has led to significant improvements in speed and interactivity. The proposed algorithm in this paper benefits from recent GPUs and achieves fully parallelized mesh simplification while preserving topological properties.
Article
Geochemistry & Geophysics
Reuma Arav, Sagi Filin, Norbert Pfeifer
Summary: In this article, a context-aware subsampling approach is proposed to reduce the data load of less important regions while retaining high resolution of objects of interest. Visual saliency measures are used to identify regions that require detail preservation, and data reduction is only applied to nonsalient regions. A hierarchical data structure based on surface nature enables progressive subsampling, with retained representative points describing the underlying surface. The proposed model is demonstrated on datasets from different scanners, and results are compared with three common simplification approaches, showing a reduced point cloud similar to the original for ROI analysis regardless of the level of simplification.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Chemistry, Analytical
Esmeide Leal, German Sanchez-Torres, John W. Branch-Bedoya, Francisco Abad, Nallig Leal
Summary: A new point cloud feature-preserving simplification algorithm is proposed to detect salient points in a given point cloud, reducing data volume while preserving relevant features. Global approach is used to detect saliencies, with feature vectors serving as basis signals for dictionary learning and sparse coding process.
Article
Chemistry, Multidisciplinary
Fei Yan, Cheng Chen, Peng Xiao, Siyu Qi, Zhiliang Wang, Ruoxiu Xiao
Summary: This study summarizes the achievements in the field of saliency prediction, including the early neurological and psychological mechanisms, the guiding role of classic models, and the development process and data comparison of classic and deep saliency prediction models. It also discusses the relationship between the model and human vision, the factors causing semantic gaps, the influences of attention in cognitive research, the limitations of the saliency model, and the emerging applications.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Analytical
Daniel Jie Yuan Chin, Ahmad Sufril Azlan Mohamed, Khairul Anuar Shariff, Mohd Nadhir Ab Wahab, Kunio Ishikawa
Summary: This study focuses on achieving near real-time surface reconstruction for large medical images, experimenting with different parameter values to study their effect on reconstruction accuracy, reconstruction and rendering time, and the number of vertices and faces. The proposed optimal parameter combination successfully balances high reconstruction accuracy, low total execution time, and reduced number of vertices and faces.
Article
Computer Science, Hardware & Architecture
Anass Nouri, Christophe Charrier, Olivier Lezoray
Summary: This paper presents a full-reference quality assessment metric based on visual saliency information. The metric uses degrees associated with each vertex of the surface mesh to compute statistical attributes reflecting the structures of the reference and distorted meshes. A comparison study of six full-reference quality assessment metrics for 3D meshes is also presented. The proposed metric is shown to be competitive with the state-of-the-art through experimental results.
Article
Computer Science, Information Systems
Sumaira Erum Zaib, Masayuki Yamamura
Summary: In this study, a Gradient Boosted Tree Regression model is proposed to extract personalized saliency map from the universal saliency map with an average accuracy of 80%. The discussion is also provided for why some images and subjects have better saliency map predictions than others.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Mathematics, Interdisciplinary Applications
Nianhua Wang, Laiping Zhang, Xiaogang Deng
Summary: In numerical simulations, mesh quality plays a direct and significant role in determining simulation accuracy. This paper proposes a new smoothing method that combines the advantages of heuristic smoothing methods and optimization-based methods using deep reinforcement learning. The method is trained and validated on 2D triangular meshes and 3D surface meshes, demonstrating its efficiency and mesh quality.
COMPUTATIONAL MECHANICS
(2023)
Article
Environmental Sciences
Zhendong Liu, Chengcheng Zhang, Haolin Cai, Wenhu Qv, Shuaizhe Zhang
Summary: This paper proposes a model simplification algorithm suitable for 3D reconstruction, which solves the problems of texture distortion and deformation in mesh simplification by utilizing the recovered 3D scene structure and calibrated images, and the experimental results demonstrate the feasibility of the algorithm.
Article
Mathematics, Applied
Cesar Blecua, Antonio Falco
Summary: This paper presents a new smoothing post-processing meshing algorithm to address the distortion and size error problems in quadrilateral meshes. The algorithm achieves a good compromise between distortion and size of each element in the mesh by using an elasticity-based argument. It can be implemented in both sequential and parallel forms, and provides a high-quality output compared to other smoothing post-processing meshing algorithms.
FINITE ELEMENTS IN ANALYSIS AND DESIGN
(2023)