Timezone: »

 
Poster
Point-Voxel CNN for Efficient 3D Deep Learning
Zhijian Liu · Haotian Tang · Yujun Lin · Song Han

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #112
in Deep Learning -- Efficient Inference Methods »

We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches are computationally inefficient. The computation cost and memory footprints of the voxel-based models grow cubically with the input resolution, making it memory-prohibitive to scale up the resolution. As for point-based networks, up to 80% of the time is wasted on dealing with the sparse data which have rather poor memory locality, not on the actual feature extraction. In this paper, we propose PVCNN that represents the 3D input data in points to reduce the memory consumption, while performing the convolutions in voxels to reduce the irregular, sparse data access and improve the locality. Our PVCNN model is both memory and computation efficient. Evaluated on semantic and part segmentation datasets, it achieves a much higher accuracy than the voxel-based baseline with 10x GPU memory reduction; it also outperforms the state-of-the-art point-based models with 7x measured speedup on average. Remarkably, the narrower version of PVCNN achieves 2x speedup over PointNet (an extremely efficient model) on part and scene segmentation benchmarks with much higher accuracy. We validate the general effectiveness of PVCNN on 3D object detection: by replacing the primitives in Frustrum PointNet with PVConv, it outperforms Frustrum PointNet++ by up to 2.4% mAP with 1.8x measured speedup and 1.4x GPU memory reduction.

Keywords: Efficient Inference Methods · Hardware and Systems · Applications · Deep Learning

Author Information

Zhijian Liu (MIT)
Haotian Tang (Shanghai Jiao Tong University)
Yujun Lin (MIT)
Song Han (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors