2020

Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation

Zhou, Hui, Zhu, Xinge, Song, Xiao et al.

Understand

State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space.

The projection methods includes spherical projection, bird-eye view projection, etc.
Although this process makes the point cloud suitable for the 2D CNN-based networks, it inevitably alters and abandons the 3D topology and geometric relations.
A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space.

Built on

Tangent convolutions for dense prediction in 3d
M. Tatarchenko, J. Park, V. Koltun, and Q.-Y. Zhou · 2008
Earlier work this paper cites.
Fully convolutional networks for semantic segmentation
J. Long, E. Shelhamer, and T. Darrell · 2015
Earlier work this paper cites.
U-net: Convolutional networks for biomedical image segmentation
O. Ronneberger, P. Fischer, and T. Brox · 2015
Earlier work this paper cites.
3d u-net: learning dense volumetric segmentation from sparse annotation
Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger · 2016
Earlier work this paper cites.
Pointnet: Deep learning on point sets for 3d classification and segmentation
C. R. Qi, H. Su, K. Mo, and L. J. Guibas · 2017
Earlier work this paper cites.
Graph attention networks
Original
P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio · 2017
Earlier work this paper cites.
Pointnet++: Deep hierarchical feature learning on point sets in a metric space
C. R. Qi, L. Yi, H. Su, and L. J. Guibas · 2017
Earlier work this paper cites.
Segcloud: Semantic segmentation of 3d point clouds
L. Tchapmi, C. Choy, I. Armeni, J. Gwak, and S. Savarese · 2017
Earlier work this paper cites.
Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs
L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille · 2017
Earlier work this paper cites.
Pyramid scene parsing network
H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia · 2017
Earlier work this paper cites.
Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud
B. Wu, A. Wan, X. Yue, and K. Keutzer · 2018
Earlier work this paper cites.
3d semantic segmentation with submanifold sparse convolutional networks
B. Graham, M. Engelcke, and L. Van Der Maaten · 2018
Earlier work this paper cites.

Similar

Encoder-decoder with atrous separable convolution for semantic image segmentation
L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam · 2018
Cited alongside, same era.
Second: Sparsely embedded convolutional detection
Y. Yan, Y. Mao, and B. Li · 2018
Cited alongside, same era.
The lovász-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
M. Berman, A. Rannen Triki, and M. B. Blaschko · 2018
Cited alongside, same era.
Splatnet: Sparse lattice networks for point cloud processing
H. Su, V. Jampani, D. Sun, S. Maji, E. Kalogerakis, M.-H. Yang, and J. Kautz · 2018
Cited alongside, same era.
Rangenet++: Fast and accurate lidar semantic segmentation
A. Milioto, I. Vizzo, J. Behley, and C. Stachniss · 2019
Cited alongside, same era.
Kpconv: Flexible and deformable convolution for point clouds
H. Thomas, C. R. Qi, J.-E. Deschaud, B. Marcotegui, F. Goulette, and L. J. Guibas · 2019
Cited alongside, same era.
Pointconv: Deep convolutional networks on 3d point clouds
W. Wu, Z. Qi, and L. Fuxin · 2019
Cited alongside, same era.
Dynamic graph cnn for learning on point clouds
Y. Wang, Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, and J. M. Solomon · 2019
Cited alongside, same era.
Semantickitti: A dataset for semantic scene understanding of lidar sequences
J. Behley, M. Garbade, A. Milioto, J. Quenzel, S. Behnke, C. Stachniss, and J. Gall · 2019
Cited alongside, same era.
Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud
B. Wu, X. Zhou, S. Zhao, X. Yue, and K. Keutzer · 2019
Cited alongside, same era.
Shape robust text detection with progressive scale expansion network
W. Wang, E. Xie, X. Li, W. Hou, T. Lu, G. Yu, and S. Shao · 2019
Cited alongside, same era.

Then

Co-occurrent features in semantic segmentation
H. Zhang, H. Zhang, C. Wang, and J. Xie · 2019
Later among the works it cites.
Polarnet: An improved grid representation for online lidar point clouds semantic segmentation
Y. Zhang, Z. Zhou, P. David, X. Yue, Z. Xi, B. Gong, and H. Foroosh · 2020
Closest in time.
Learning to segment 3d point clouds in 2d image space
Y. Lyu, X. Huang, and Z. Zhang · 2020
Closest in time.
3d-mpa: Multi-proposal aggregation for 3d semantic instance segmentation
F. Engelmann, M. Bokeloh, A. Fathi, B. Leibe, and M. Nießner · 2020
Closest in time.
Fusion-aware point convolution for online semantic 3d scene segmentation
J. Zhang, C. Zhu, L. Zheng, and K. Xu · 2020
Closest in time.
Reconfigurable voxels: A new representation for lidar-based point clouds
Original
T. Wang, X. Zhu, and D. Lin · 2020
Closest in time.
Occuseg: Occupancy-aware 3d instance segmentation
L. Han, T. Zheng, L. Xu, and L. Fang · 2020
Closest in time.
Ssn: Shape signature networks for multi-class object detection from point clouds
Original
X. Zhu, Y. Ma, T. Wang, Y. Xu, J. Shi, and D. Lin · 2020
Closest in time.
Tensor low-rank reconstruction for semantic segmentation
Original
W. Chen, X. Zhu, R. Sun, J. He, R. Li, X. Shen, and B. Yu · 2020
Closest in time.
Squeezesegv3: Spatially-adaptive convolution for efficient point-cloud segmentation
Original
C. Xu, B. Wu, Z. Wang, W. Zhan, P. Vajda, K. Keutzer, and M. Tomizuka · 2020
Closest in time.
Randla-net: Efficient semantic segmentation of large-scale point clouds
Q. Hu, B. Yang, L. Xie, S. Rosa, Y. Guo, Z. Wang, N. Trigoni, and A. Markham · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…