Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs
2017 IEEE International Conference on Computer Vision (ICCV)(2017)
摘要
We present a deep convolutional decoder architecture that can generate volumetric 3D outputs in a compute- and memory-efficient manner by using an octree representation. The network learns to predict both the structure of the octree, and the occupancy values of individual cells. This makes it a particularly valuable technique for generating 3D shapes. In contrast to standard decoders acting on regular voxel grids, the architecture does not have cubic complexity. This allows representing much higher resolution outputs with a limited memory budget. We demonstrate this in several application domains, including 3D convolutional autoencoders, generation of objects and whole scenes from high-level representations, and shape from a single image.
更多查看译文
关键词
3D convolutional autoencoders,high-level representations,octree generating networks,efficient convolutional architectures,high-resolution 3D outputs,deep convolutional decoder architecture,octree representation,occupancy values,regular voxel grids
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络