Multiview stereo and silhouette fusion via minimizing generalized reprojection error

Li, Zhaoxin; Wang, Kuanquan; Jia, Wenyan; Chen, Hsin-Chen; Zuo, Wangmeng; Meng, Deyu; Sun, Mingui

doi:10.1016/j.imavis.2014.10.008

Cited by 4 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other smoothing methods, such as mean curvature motion [35], [36] and gradient flow [6], have been studied and applied to mesh-based MVS [5], [30]. To improve the computational efficiency, different approximations, such as Laplacian approximation [7], [20], [29], umbrella operator, [19] and paraboloid approximation [28], have been proposed. Higher order derivatives, e.g., combination of the first-and second-order Laplace [43], thin-plate energy [31], [32], have been suggested to handle artificial shrinkage of small components and to penalize strong bending.…”

Section: Related Workmentioning

confidence: 99%

“…We can then have an interesting connection between the derivatives of reprojection errors and guided image filtering. Based on (13), (18)- (20), Eq. (17) can be reformulated as:…”

Section: A Detail-preserving Inter-image Similarity Measurementioning

confidence: 99%

“…Another line of methods compare the image pixels with rendered surface textures [9], [28] by implicitly assuming controlled lighting environments. The reprojection error minimization framework, which is also known as reprojection error functional [5], [20], [35], [36], attempts to solve the MVS problem by comparing the observed and predicted values of pixels generated from the reconstructed surface. The total consistency of the mesh surface is measured on image space instead of 3D surface space to alleviate projective distortion.…”

Section: Related Workmentioning

confidence: 99%

“…The silhouettes of an object can be fused to ensure that the reconstructed surface preserves the protrusions and indentions. They can be adopted in either volumetric-based [21]- [23] or meshbased methods [9], [19], [20]. However, the incorporation of silhouettes cannot guarantee the preservation of fine-scale surface details and sharp features that are not on the contour generators of surface.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Detail-Preserving and Content-Aware Variational Multi-View Stereo Reconstruction

Wang

Zuo

et al. 2016

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Abstract-Accurate recovery of 3D geometrical surfaces from calibrated 2D multi-view images is a fundamental yet active research area in computer vision. Despite the steady progress in multi-view stereo reconstruction, most existing methods are still limited in recovering fine-scale details and sharp features while suppressing noises, and may fail in reconstructing regions with few textures. To address these limitations, this paper presents a Detail-preserving and Content-aware Variational (DCV) multiview stereo method, which reconstructs the 3D surface by alternating between reprojection error minimization and mesh denoising. In reprojection error minimization, we propose a novel inter-image similarity measure, which is effective to preserve fine-scale details of the reconstructed surface and builds a connection between guided image filtering and image registration. In mesh denoising, we propose a content-aware p -minimization algorithm by adaptively estimating the p value and regularization parameters based on the current input. It is much more promising in suppressing noise while preserving sharp features than conventional isotropic mesh smoothing. Experimental results on benchmark datasets demonstrate that our DCV method is capable of recovering more surface details, and obtains cleaner and more accurate reconstructions than state-of-the-art methods. In particular, our method achieves the best results among all published methods on the Middlebury dino ring and dino sparse ring datasets in terms of both completeness and accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

“…We can then have an interesting connection between the derivatives of reprojection errors and guided image filtering. Based on (13), (18)- (20), Eq. (17) can be reformulated as:…”

Section: A Detail-preserving Inter-image Similarity Measurementioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Detail-Preserving and Content-Aware Variational Multi-View Stereo Reconstruction

Wang

Zuo

et al. 2016

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

Object detection using hybridization of static and dynamic feature spaces and its exploitation by ensemble classification

Murtza

Khan

Akhtar

2017

Neural Comput & Applic

View full text Add to dashboard Cite

An automatic electronic instrument for accurate measurements of food volume and density

Yuan¹,

Hu²,

Hong³

et al. 2020

Public Health Nutr.

Self Cite

View full text Add to dashboard Cite

Objective: Accurate measurements of food volume and density are often required as ‘gold standards’ for calibration of image-based dietary assessment and food database development. Currently, there is no specialised laboratory instrument for these measurements. We present the design of a new volume of density (VD) meter to bridge this technological gap. Design: Our design consists of a turntable, a load sensor, a set of cameras and lights installed on an arc-shaped stationary support, and a microcomputer. It acquires an array of food images, reconstructs a 3D volumetric model, weighs the food and calculates both food volume and density, all in an automatic process controlled by the microcomputer. To adapt to the complex shapes of foods, a new food surface model, derived from the electric field of charged particles, is developed for 3D point cloud reconstruction of either convex or concave food surfaces. Results: We conducted two experiments to evaluate the VD meter. The first experiment utilised computer-synthesised 3D objects with prescribed convex and concave surfaces of known volumes to investigate different food surface types. The second experiment was based on actual foods with different shapes, colours and textures. Our results indicated that, for synthesised objects, the measurement error of the electric field-based method was <1 %, significantly lower compared with traditional methods. For real-world foods, the measurement error depended on the types of food volumes (detailed discussion included). The largest error was approximately 5 %. Conclusion: The VD meter provides a new electronic instrument to support advanced research in nutrition science.

show abstract

Multiview stereo and silhouette fusion via minimizing generalized reprojection error

Cited by 4 publications

References 46 publications

Detail-Preserving and Content-Aware Variational Multi-View Stereo Reconstruction

Detail-Preserving and Content-Aware Variational Multi-View Stereo Reconstruction

Object detection using hybridization of static and dynamic feature spaces and its exploitation by ensemble classification

An automatic electronic instrument for accurate measurements of food volume and density

Contact Info

Product

Resources

About