Can I read Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective on EtoBox?

Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective by Chen, Xiaokang; Tang, Jiaxiang; Wang, Jingbo; Zeng, Gang is a scholarly article available to read on EtoBox.

What is Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective about?

We revisit Semantic Scene Completion (SSC), a useful task to predict the semantic and occupancy representation of 3D scenes, in this paper. A number of methods for this task are always based on voxelized scene representations for keeping local scene structure. However, due to the existence of visible empty voxels, these methods always suffer from heavy computation redundancy when the network goes deeper, and thus limit the completion quality. To address this dilemma, we propose our novel point-voxel aggregation network for this task. Firstly, we transfer the voxelized scenes to point clouds by removing these visible empty voxels and adopt a deep point stream to capture semantic information from the scene efficiently. Meanwhile, a light-weight voxel stream containing only two 3D convolution layers preserves local structures of the voxelized scenes. Furthermore, we design an anisotropic voxel aggregation operator to fuse the structure details from the voxel stream into the point stream, and a semantic-aware propagation module to enhance the up-sampling process in the point stream by semantic labels. We demonstrate that our model surpasses state-of-the-arts on two benchmarks by a larg

Author

Chen, Xiaokang; Tang, Jiaxiang; Wang, Jingbo; Zeng, Gang

Published

2021

Language

EN