论文标题
改进了具有多视图深度图的3D形状的建模
Improved Modeling of 3D Shapes with Multi-view Depth Maps
论文作者
论文摘要
我们提出了一个简单而有效的通用框架，用于通过利用CNN的2D图像生成中的最新进展来建模3D形状。仅使用对象的一个深度图像，我们可以输出3D对象的密集多视图深度图表示。我们的简单编码器数据编码器框架由新颖的身份编码器和类条件观点生成器组成，生成了3D一致的深度图。我们的实验结果证明了我们方法的两倍优势。首先，我们可以直接借用在2D图像域到3D的架构。其次，我们可以有效地生成具有低计算存储器的高分辨率3D形状。我们的定量评估表明，我们的方法优于现有的深度图方法，用于重建和合成3D对象，并且与其他表示，例如点云，体素电网和隐式函数竞争。
We present a simple yet effective general-purpose framework for modeling 3D shapes by leveraging recent advances in 2D image generation using CNNs. Using just a single depth image of the object, we can output a dense multi-view depth map representation of 3D objects. Our simple encoder-decoder framework, comprised of a novel identity encoder and class-conditional viewpoint generator, generates 3D consistent depth maps. Our experimental results demonstrate the two-fold advantage of our approach. First, we can directly borrow architectures that work well in the 2D image domain to 3D. Second, we can effectively generate high-resolution 3D shapes with low computational memory. Our quantitative evaluations show that our method is superior to existing depth map methods for reconstructing and synthesizing 3D objects and is competitive with other representations, such as point clouds, voxel grids, and implicit functions.
