We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks. SGC is orthogonal to group convolution, which works on spatial dimensions rather than feature channel dimension. It divides input voxels into different groups, then conducts 3D sparse convolution on these separated groups. As only valid voxels are considered when performing convolution, computation can be significantly reduced with a slight loss of accuracy. The proposed operations are validated on semantic scene completion task, which aims to predict a complete 3D volume with semantic labels from a single depth image. With SGC, we further present an efficient 3D sparse convolutional network, which harnesses a multiscale architecture and a coarse-to-fine prediction strategy. Evaluations are conducted on the SUNCG dataset, achieving state-of-the-art performance and fast speed.
Authors
Yurong Chen
Senior Research Director & Principle Research Scientist, Cognitive Computing Lab, Intel Labs China
Jiahui Zhang
Hao Zhao
Li Zhang
Hongen Liao
Related Content
On Offline Evaluation of Vision-based Driving Models
Autonomous driving models should ideally be evaluated by deploying them on a fleet of physical vehicles in the real world....
CARLA: An Open Urban Driving Simulator
We introduce CARLA, an open-source simulator for autonomous driving research. CARLA has been developed from the ground up to support....
Colored Point Cloud Registration Revisited
We present an algorithm for aligning two colored point clouds. The key idea is to optimize a joint photometric and....
End-to-End Driving via Conditional Imitation Learning
Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained....