Beyond Farthest Point Sampling in Point-Wise Analysis
release_kkjkk2lmtfdxbnuy5phyarbviy
by
Yiqun Lin, Lichang Chen, Haibin Huang, Chongyang Ma, Xiaoguang Han, Shuguang Cui
2021
Abstract
Sampling, grouping, and aggregation are three important components in the
multi-scale analysis of point clouds. In this paper, we present a novel
data-driven sampler learning strategy for point-wise analysis tasks. Unlike the
widely used sampling technique, Farthest Point Sampling (FPS), we propose to
learn sampling and downstream applications jointly. Our key insight is that
uniform sampling methods like FPS are not always optimal for different tasks:
sampling more points around boundary areas can make the point-wise
classification easier for segmentation. Towards the end, we propose a novel
sampler learning strategy that learns sampling point displacement supervised by
task-related ground truth information and can be trained jointly with the
underlying tasks. We further demonstrate our methods in various point-wise
analysis architectures, including semantic part segmentation, point cloud
completion, and keypoint detection. Our experiments show that jointly learning
of the sampler and task brings remarkable improvement over previous baseline
methods.
In text/plain
format
Archived Files and Locations
application/pdf 6.2 MB
file_tfbfmthifjgc5l4doy6os6l5qm
|
arxiv.org (repository) web.archive.org (webarchive) |
2107.04291v1
access all versions, variants, and formats of this works (eg, pre-prints)