IEEE Trans Vis Comput Graph. 2017 Jul;23(7):1809-1822. doi: 10.1109/TVCG.2016.2553102. Epub 2016 Apr 12.
We present a novel approach for constructing a complete 3D model for an object from a single RGBD image. Given an image of an object segmented from the background, a collection of 3D models of the same category are non-rigidly aligned with the input depth, to compute a rough initial result. A volumetric-patch-based optimization algorithm is then performed to refine the initial result to generate a 3D model that not only is globally consistent with the overall shape expected from the input image but also possesses geometric details similar to those in the input image. The optimization with a set of high-level constraints, such as visibility, surface confidence and symmetry, can achieve more robust and accurate completion over state-of-the art techniques. We demonstrate the efficiency and robustness of our approach with multiple categories of objects with various geometries and details, including busts, chairs, bikes, toys, vases and tables.
我们提出了一种从单个 RGBD 图像构建完整 3D 模型的新方法。给定一个从背景中分割出的物体图像，我们将同一类别的一系列 3D 模型与输入的深度进行非刚性对齐，以计算粗略的初始结果。然后，执行基于体素面片的优化算法来细化初始结果，以生成一个不仅与从输入图像中预期的整体形状全局一致，而且具有与输入图像相似的几何细节的 3D 模型。通过一组高级约束（如可见性、表面置信度和对称性）进行优化，可以比最先进的技术实现更稳健和准确的完成。我们通过具有各种几何形状和细节的多个物体类别展示了我们方法的效率和鲁棒性，包括半身像、椅子、自行车、玩具、花瓶和桌子。
