[1907.03739] Point-Voxel CNN for Efficient 3D Deep Learning

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 structuring the irregular 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 largely reduce the irregular data access and improve the locality. Our PVCNN model is both memory and computation efficient. Evaluated on semantic and part segmentation datasets, it achieves much higher accuracy than the voxel-based baseline with 10x GPU memory reduction; it also outperf

1 mentions: @momiji_fullmoon
Date: 2019/09/13 03:48

Related Entries

Read more Deep Learning for NLP Best Practices
97 users, 0 mentions 2018/04/22 03:40
Read more The major advancements in Deep Learning in 2016 | Tryolabs Blog
0 users, 0 mentions 2018/04/22 03:40
Read more Deep Learningを用いた教師なし画像検査の論文調査 GAN/SVM/Autoencoderとか .pdf
0 users, 0 mentions 2018/10/09 06:53
Read more データマイニングコンペティションサイト Kaggle にも Deep Learning ブームがきてるかと思ったのでまとめる - 糞糞糞ネット弁慶
0 users, 0 mentions 2018/10/14 06:16
Read more Chainerで学ぶdeep learning
0 users, 0 mentions 2018/04/22 03:40