Point sets obtained from computer vision techniques are often noisy and non-uniform. We present a new method of surface reconstruction that can handle such data sets using anisotropic basis functions. Our reconstructi...
详细信息
ISBN:
(纸本)0769511430
Point sets obtained from computer vision techniques are often noisy and non-uniform. We present a new method of surface reconstruction that can handle such data sets using anisotropic basis functions. Our reconstruction algorithm draws upon the work in variational implicit surfaces for constructing smooth and seamless 3D surfaces. Implicit functions are often formulated as a sum of weighted basis functions that are radially symmetric. Using radially symmetric basis functions inherently assumes, however that the surface to be reconstructed is, everywhere, locally symmetric. Such an assumption is true only at planar regions, and hence, reconstruction using isotropic basis is insufficient to recover objects that exhibit sharp features. We preserve sharp features using anisotropic basis that allow the surface to vary locally. The reconstructed surface is sharper along edges and at corner points. We determine the direction of anisotropy at a point by performing principal component analysis of the data points in a small neighborhood. The resulting field of principle directions across the surface is smoothed through tensor filtering. We have applied the anisotropic basis functions to reconstruct surfaces from noisy synthetic 3D data and from real range data obtained from space carving.
Deep learning models for organ contouring in radiotherapy are poised for clinical usage, but currently, there exist few tools for automated quality assessment (QA) of the predicted contours. Using Bayesian models and ...
详细信息
We present a novel de-homogenization approach for efficient design of high-resolution load-bearing structures. The proposed approach builds upon a streamline-based parametrization of the design domain, using a set of ...
详细信息
There can be no debate that Information Mining Projects cause processing tools to arise with the sole purpose of converting available organization data into useful knowledge on account of decision-making. Considering ...
详细信息
In this paper, we describe a digital library initiative for non-textual documents. The proposed framework will integrate different types of content-repositories - each one specialized for a specific multimedia domain ...
详细信息
In this paper, we describe a digital library initiative for non-textual documents. The proposed framework will integrate different types of content-repositories - each one specialized for a specific multimedia domain - into one seamless system and will add features such as automatic annotation, full-text retrieval and recommender services to non-textual documents. Two multimedia domains, 3D graphics and music, will be introduced. The repositories can be searched using both textual (metadata-based) and non-textual retrieval mechanisms (e.g. using a complex sketch-based interface for searching in 3D-models or a query-by-humming interface for music). Domain-specific metadata models are developed and workflows for automated content-based data analysis and indexing proposed.
暂无评论