Efficient Depth Propagation for Constructing a Layered Depth Image from a Single Image
Efficient Depth Propagation for Constructing a Layered Depth Image from a Single Image
复制标题
DOI：
10.1111/cgf.12496
复制
发表时间：
2014-10
影响因子：
2.5
通讯作者：
S. Iizuka;Yuki Endo;Yoshihiro Kanamori;J. Mitani;Y. Fukui
中科院分区：
文献类型：
--
作者：
S. Iizuka;Yuki Endo;Yoshihiro Kanamori;J. Mitani;Y. Fukui
在本文中，我们提出了一种通过稀疏用户输入构建 3D 场景的交互技术。我们以分层深度图像（LDI）的形式表示 3D 场景，该图像由前景层和背景层组成，每个层都有相应的纹理和深度图。给定用户指定的稀疏深度输入，深度图是基于超像素使用测地距离加权插值和优化框架来计算的。该计算立即完成，这允许用户交互式地编辑 LDI。此外，我们的技术使用深度不连续性自动估计遮挡区域的深度和纹理。在我们的界面中，用户直接在 3D 模型上绘制笔画。绘制的笔划充当 3D 手柄，用户可以通过实时反馈轻松直观地拉出或推动 3D 表面。我们展示了我们的技术能够对 LDI 进行高效建模，从而产生足够的 3D 效果。
In this paper, we propose an interactive technique for constructing a 3D scene via sparse user inputs. We represent a 3D scene in the form of a Layered Depth Image (LDI) which is composed of a foreground layer and a background layer, and each layer has a corresponding texture and depth map. Given user‐specified sparse depth inputs, depth maps are computed based on superpixels using interpolation with geodesic‐distance weighting and an optimization framework. This computation is done immediately, which allows the user to edit the LDI interactively. Additionally, our technique automatically estimates depth and texture in occluded regions using the depth discontinuity. In our interface, the user paints strokes on the 3D model directly. The drawn strokes serve as 3D handles with which the user can pull out or push the 3D surface easily and intuitively with real‐time feedback. We show our technique enables efficient modeling of LDI that produce sufficient 3D effects.