期刊
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
卷 -, 期 -, 页码 2575-2583出版社
IEEE
DOI: 10.1109/CVPR.2017.276
关键词
-
类别
资金
- Spanish Government
- European Regional Development Fund (ERDF) [DPI2014-55826-R]
- Spanish grant program FPI-MICINN
- ERC Consolidator Grant 3DReloaded
We present a novel strategy to shrink and constrain a 3D model, represented as a smooth spline-like surface, within the visual hull of an object observed from one or multiple views. This new 'background' or 'silhouette' term combines the efficiency of previous approaches based on an image-plane distance transform with the accuracy of formulations based on raycasting or ray potentials. The overall formulation is solved by alternating an inner nonlinear minimization (raycasting) with a joint optimization of the surface geometry, the camera poses and the data correspondences. Experiments on 3D reconstruction and object tracking show that the new formulation corrects several deficiencies of existing approaches, for instance when modelling non-convex shapes. Moreover, our proposal is more robust against defects in the object segmentation and inherently handles the presence of uncertainty in the measurements (e.g. null depth values in images provided by RGB-D cameras).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据