-
Supervized Segmentation with Graph-Structured Deep Metric Learning
We present a fully-supervized method for learning to segment data struct...
read it
-
Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
We propose a novel deep learning-based framework to tackle the challenge...
read it
-
Deep Projective 3D Semantic Segmentation
Semantic segmentation of 3D point clouds is a challenging problem with n...
read it
-
LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices
Deep convolutional neural networks (CNNs) have shown outstanding perform...
read it
-
3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN
Deep learning on point clouds has made a lot of progress recently. Many ...
read it
-
Inferring Point Cloud Quality via Graph Similarity
We propose the GraphSIM – an objective metric to accurately predict the ...
read it
-
Learning Deep Structure-Preserving Image-Text Embeddings
This paper proposes a method for learning joint embeddings of images and...
read it
Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning
We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents high contrasts. The embeddings are computed using a lightweight neural network operating on the points' local neighborhood. Finally, we formulate point cloud oversegmentation as a graph partition problem with respect to the learned embeddings. This new approach allows us to set a new state-of-the-art in point cloud oversegmentation by a significant margin, on a dense indoor dataset (S3DIS) and a sparse outdoor one (vKITTI). Our best solution requires over five times fewer superpoints to reach similar performance than previously published methods on S3DIS. Furthermore, we show that our framework can be used to improve superpoint-based semantic segmentation algorithms, setting a new state-of-the-art for this task as well.
READ FULL TEXT
Comments
There are no comments yet.