摘要
This paper introduces a novel method of surface refinement for free-viewpoint video of dynamic scenes. Unlike previous approaches, the method presented here uses both visual hull and silhouette contours to constrain refinement of view-dependent depth maps from wide baseline views. A technique for extracting silhouette contours as rims in 3D from the view-dependent visual hull (VDVH) is presented. A new method for improving correspondence is introduced, where refinement of the VDVH is posed as a global problem in projective ray space. Artefacts of global optimisations are reduced by incorporating rims as constraints. Real time rendering of virtual views in a free-viewpoint video system is achieved using an image+depth representation for each real view. Results illustrate the high quality of rendered views achieved through this refinement technique.
摘要译文
本文介绍了一种新型表面细化的动态场景自由视点视频的方法。不同于以往的方法，这里介绍的方法同时使用可视船体和剪影轮廓，从广泛的基线意见约束的角度依赖深度贴图细化。一种技术提取的剪影轮廓从视图依赖视觉船体（VDVH）在3D轮辋呈现。为提高通信的新方法被引入，其中VDVH的细化提出在投影光线空间的全球性问题。全球最佳化的文物是通过将轮辋的限制减少。在自由视点视频系统虚拟次实时渲染是使用对于每个真实视图的图像深度表示来实现。结果表明，通过这种细化的技术实现渲染视图的高品质。
Miller, G.; Starck, J.; Hilton, A.. Proj ective Surface Refinement for Free-Viewpoint Video[C]//Visual Media Production, 2006. CVMP 2006. 3rd European Conference on, London, 2006, IEEE, 2006: 153-162