TY - GEN
T1 - 3D Geometry-Aware Semantic Labeling of Outdoor Street Scenes
AU - Zhong, Yiran
AU - Dai, Yuchao
AU - Li, Hongdong
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/26
Y1 - 2018/11/26
N2 - This paper is concerned with the problem of how to better exploit 3D geometric information for dense semantic image labeling. Existing methods often treat the available 3D geometry information (e.g., 3D depth-map) simply as an additional image channel besides the R-G-B color channels, and apply the same technique for RGB image labeling. In this paper, we demonstrate that directly performing 3D convolution in the framework of a residual connected 3D voxel top-down modulation network can lead to superior results. Specifically, we propose a 3D semantic labeling method to label outdoor street scenes whenever a dense depth map is available. Experiments on the 'Synthia' and 'Cityscape' datasets show our method outperforms the state-of-the-art methods, suggesting such a simple 3D representation is effective in incorporating 3D geometric information.
AB - This paper is concerned with the problem of how to better exploit 3D geometric information for dense semantic image labeling. Existing methods often treat the available 3D geometry information (e.g., 3D depth-map) simply as an additional image channel besides the R-G-B color channels, and apply the same technique for RGB image labeling. In this paper, we demonstrate that directly performing 3D convolution in the framework of a residual connected 3D voxel top-down modulation network can lead to superior results. Specifically, we propose a 3D semantic labeling method to label outdoor street scenes whenever a dense depth map is available. Experiments on the 'Synthia' and 'Cityscape' datasets show our method outperforms the state-of-the-art methods, suggesting such a simple 3D representation is effective in incorporating 3D geometric information.
UR - http://www.scopus.com/inward/record.url?scp=85059754273&partnerID=8YFLogxK
U2 - 10.1109/ICPR.2018.8545378
DO - 10.1109/ICPR.2018.8545378
M3 - Conference contribution
T3 - Proceedings - International Conference on Pattern Recognition
SP - 2343
EP - 2349
BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 24th International Conference on Pattern Recognition, ICPR 2018
Y2 - 20 August 2018 through 24 August 2018
ER -