3D Graph Neural Networks for RGBD Semantic Segmentation

Xiaojuan Qi, Renjie Liao, Jiaya Jia, Sanja Fidler, Raquel Urtasun; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 5199-5208

Abstract


RGBD semantic segmentation requires joint reasoning about 2D appearance and 3D geometric information. In this paper we propose a 3D graph neural network (3DGNN) that builds a k-nearest neighbor graph on top of 3D point cloud. Each node in the graph corresponds to a set of points and is associated with a hidden representation vector initialized with an appearance feature extracted by a unary CNN from 2D images. Relying on recurrent functions, every node dynamically updates its hidden representation based on the current status and incoming messages from its neighbors. This propagation model is unrolled for a certain number of time steps and the final per-node representation is used for predicting the semantic class of each pixel. We use back-propagation through time to train the model. Extensive experiments on NYUD2 and SUN-RGBD datasets demonstrate the effectiveness of our approach.

Related Material


[pdf] [video]
[bibtex]
@InProceedings{Qi_2017_ICCV,
author = {Qi, Xiaojuan and Liao, Renjie and Jia, Jiaya and Fidler, Sanja and Urtasun, Raquel},
title = {3D Graph Neural Networks for RGBD Semantic Segmentation},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}