Improving RGB-D based 3D Reconstruction by Combining Voxels and Points
Improving RGB-D based 3D Reconstruction by Combining Voxels and Points
复制标题
通过结合体素和点改进基于 RGB-D 的 3D 重建
DOI：
10.1007/s00371-022-02661-5
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Guodong Lu
中科院分区：
文献类型：
--
作者：
Xinqi Liu;JituoLi;Guodong Lu
提出了一种基于RGB-D数据流的灵活三维重建方法。与以往的方法使用纯体素或纯点作为表示，我们的作品提出了一种新的表示相结合的体素和点，以提高重建精度。一个关键的见解是，点可以存储额外的深度数据，而这些数据不是由常规体素采样的。因此，通过整合点和体素，由于更高的数据利用率，可以加速3D重建过程。此外，存储在点中的深度信息用于通过深度图像细化方法来细化有噪声的深度图像，从而提高重建的形状质量。进行了广泛的比较实验，包括不同的表示（纯体素/点）和各种方法（基于融合/基于学习和在线/离线），以说明我们的工作的有效性。实验结果表明，我们的方法可以实现实时性能，有效地避免文物，并达到国家的最先进的准确性水平。更重要的是，我们提供了一个新的想法来平衡内存开销和重建精度之间的冲突。
We propose a flexible 3D reconstruction method based on the RGB-D data stream. Compared to previous methods using pure voxels or pure points as representations, our works propose a new representation combining voxels and points to improve the reconstruction accuracy. A key insight is that points can store additional depth data that are not sampled by regular voxels. Thus, by integrating points and voxels, the 3D reconstruction process can be accelerated due to higher data utilization. Furthermore, depth information stored in points is used to refine the noisy depth image through a depth image refinement method, consequently improving the reconstructed shape quality. Extensive comparative experiments are performed including different representations (pure voxels/points) and various methods (fusion-based/learning-based and online/offline) to illustrate the effectiveness of our work. Experimental results demonstrate that our method can achieve real-time performance, effectively avoid artifacts, and reach state-of-the-art accuracy levels. More importantly, we provide a novel idea to balance the conflict between memory overhead and reconstruction accuracy.