arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.09987cs.CV
收藏

高分辨率三维物体表示的多视点轮廓和深度分解

Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation

McGill University(麦吉尔大学)

Edward Smith, Scott Fujimoto, David Meger

摘要:

我们考虑将深生成形状模型缩放到高分辨率的问题。从对象的规范视图表示中提取动机,我们引入了一种新的方法,用于通过对六个正交深度投影执行超分辨率的网络在体素空间中对3D对象进行快速上采样。这使我们能够生成高分辨率的对象,比直接在3D中工作的方法更有效地缩放。我们将二维深度超分辨率问题分解为轮廓和深度预测,以捕获结构和细节。这使得我们的方法比单个网络更容易生成尖锐的边缘。我们评估我们的工作在多个实验有关高分辨率的3D对象,并显示我们的系统能够准确地预测新的对象的分辨率高达512 $\mathbf{\times}$ 512 $\mathbf{\times}$ 512 -最高分辨率报告这项任务。我们在ShapeNet数据集上从RGB图像进行3D对象重建方面实现了最先进的性能,并进一步展示了第一种有效的3D超分辨率方法。

英文摘要:

We consider the problem of scaling deep generative shape models to high-resolution. Drawing motivation from the canonical view representation of objects, we introduce a novel method for the fast up-sampling of 3D objects in voxel space through networks that perform super-resolution on the six orthographic depth projections. This allows us to generate high-resolution objects with more efficient scaling than methods which work directly in 3D. We decompose the problem of 2D depth super-resolution into silhouette and depth prediction to capture both structure and fine detail. This allows our method to generate sharp edges more easily than an individual network. We evaluate our work on multiple experiments concerning high-resolution 3D objects, and show our system is capable of accurately predicting novel objects at resolutions as large as 512$\mathbf{\times}$512$\mathbf{\times}$512 -- the highest resolution reported for this task. We achieve state-of-the-art performance on 3D object reconstruction from RGB images on the ShapeNet dataset, and further demonstrate the first effective 3D super-resolution method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑