Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing

About

Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of the elusive shape requires sufficiently contextual semantic information, yet few works devote to this. Here we propose DensePoint, a general architecture to learn densely contextual representation for point cloud processing. Technically, it extends regular grid CNN to irregular point configuration by generalizing a convolution operator, which holds the permutation invariance of points, and achieves efficient inductive learning of local patterns. Architecturally, it finds inspiration from dense connection mode, to repeatedly aggregate multi-level and multi-scale semantics in a deep hierarchy. As a result, densely contextual information along with rich semantics, can be acquired by DensePoint in an organic manner, making it highly effective. Extensive experiments on challenging benchmarks across four tasks, as well as thorough model analysis, verify DensePoint achieves the state of the arts.

Yongcheng Liu, Bin Fan, Gaofeng Meng, Jiwen Lu, Shiming Xiang, Chunhong Pan• 2019

Related benchmarks

TaskDatasetResultRank
Part SegmentationShapeNetPart (test)
mIoU (Inst.)86.4
312
3D Object ClassificationModelNet40 (test)
Accuracy93.2
302
3D Point Cloud ClassificationModelNet40 (test)
OA93.2
297
Shape classificationModelNet40 (test)
OA93.2
255
3D Shape ClassificationModelNet40 (test)
Accuracy93.2
227
Part SegmentationShapeNetPart
mIoU (Instance)86.4
198
Object ClassificationModelNet40 (test)
Accuracy93.2
180
ClassificationModelNet40 (test)
Accuracy93.2
99
3D Point Cloud ClassificationModelNet40
Accuracy92.8
69
3D shape recognitionModelNet10 (test)
Accuracy96.6
64
Showing 10 of 18 rows

Other info

Code

Follow for update