Skip to search formSkip to main contentSkip to account menu
- Corpus ID: 160010091
@article{Biasutti2019RIUNetES, title={RIU-Net: Embarrassingly simple semantic segmentation of 3D LiDAR point cloud}, author={Pierre Biasutti and Aur{\'e}lie Bugeau and Jean-François Aujol and Mathieu Br{\'e}dif}, journal={ArXiv}, year={2019}, volume={abs/1905.08748}, url={https://api.semanticscholar.org/CorpusID:160010091}}
- P. Biasutti, Aurélie Bugeau, Mathieu Brédif
- Published in arXiv.org 21 May 2019
- Computer Science, Environmental Science, Engineering
Experiments show that RIU-Net, despite being very simple, offers results that are comparable to the state-of-the-art of range-image based methods, and it is demonstrated that this architecture is able to operate at 90fps on a single GPU, which enables deployment for real-time segmentation.
16 Citations
1
7
7
2
Figures and Tables from this paper
- figure 1
- figure 2
- figure 3
- table I
Topics
RIU-Net (opens in a new tab)PointSeg (opens in a new tab)Point Cloud (opens in a new tab)Semantic Segmentation (opens in a new tab)3D Lidars (opens in a new tab)Range Images (opens in a new tab)Real Time Segmentation (opens in a new tab)Medical Images (opens in a new tab)U-Net (opens in a new tab)State Of The Art (opens in a new tab)
16 Citations
- P. BiasuttiV. LepetitMathieu BrédifJean-François AujolAurélie Bugeau
- 2019
Environmental Science, Computer Science
ICCV 2019
This work proposes an end-to-end architecture for LiDAR point cloud semantic segmentation that efficiently solves the problem as an image processing problem and outperforms the state-of-the-art by a large margin on the KITTI dataset.
- 2
- P. BiasuttiV. LepetitJean-François AujolMathieu BrédifAurélie Bugeau
- 2019
Computer Science, Environmental Science
2019 IEEE/CVF International Conference on…
An end-to-end architecture for LiDAR point cloud semantic segmentation that efficiently solves the problem as an image processing problem and outperforms the state-of-the-art by a large margin on the KITTI dataset.
- 34
- Highly Influenced[PDF]
- Tzu-Hsuan ChenT. Chang
- 2022
Computer Science, Engineering
IEEE Transactions on Intelligent Vehicles
Experiments show that RangeSeg outperforms the state-of-the-art semantic segmentation methods with enormous speedup and improves the instance-level segmentation performance on small and far objects.
- 42 [PDF]
- Kiran AkadasShankar Gangisetty
- 2020
Computer Science, Engineering
ACCV Workshops
This paper proposes a lightweight semantic segmentation network for large-scale point clouds which consists of grid subsampling, dilated convolutions, and Gaussian error linear unit activation for gaining better performance.
- 8
- PDF
- Yunbo RaoMenghan ZhangZhanglin ChengJunmin XueJ. PuZairong Wang
- 2021
Computer Science, Engineering
Sensors
A compact but flexible framework is introduced for performing segmentation to the semantics of point clouds concurrently, contribute to more precise segmentation and based on semantics labels, a novel DCRF model is elaborated to refine the result of segmentation.
- Biao GaoYancheng PanChengkun LiSibo GengHuijing Zhao
- 2020
Environmental Science, Computer Science
ArXiv
A review of existing 3D datasets and 3D semantic segmentation methods and efforts to solve data hungry problems are summarized for both 3D LiDAR-focused methods and general-purpose methods.
- 25 [PDF]
- Lele WangYingping Huang
- 2022
Engineering, Computer Science
IEEE Intelligent Transportation Systems Magazine
This article aims to provide a comprehensive survey of 3D point cloud and DL-based methods for scene understanding in autonomous driving, mainly divided into two subtasks: object detection and semantic segmentation.
- 9
- Highly Influenced
- Biao GaoYancheng PanChengkun LiSibo GengHuijing Zhao
- 2020
Engineering, Environmental Science
This is the first work to analyze the data hunger problem for 3D semantic segmentation using deep learning techniques that are addressed in the literature review, statistical analysis, andCross-dataset and cross-algorithm experiments.
- 8
- Yin ZhangGuoquan RenGuojie KongHui Xie
- 2020
Computer Science, Engineering
2020 International Conference on Artificial…
Experiments show that the multi-level feature fusion method can increase the performance of road segmentation, and the FCN model has a general segmentation effect in complex road scenes.
- Tomasz NowakKrzysztof ĆwianP. Skrzypczyński
- 2021
Engineering, Computer Science
Sensors
It is demonstrated that non-stationary objects can be detected using neural network models trained with 2-D grayscale images in the supervised or unsupervised training process, which makes it possible to alleviate the lack of large datasets of 3-D laser scans with point-wise annotations for non- stationary objects.
...
...
22 References
- Y. WangTianyue ShiPeng YunL. TaiMing Liu
- 2018
Computer Science, Engineering
ArXiv
This paper takes the spherical image, which is transformed from the 3D LiDAR point clouds, as input of the convolutional neural networks (CNNs) to predict the point-wise semantic map, which makes it quite compatible for autonomous driving applications.
- 111
- Highly Influential[PDF]
- P. BiasuttiJean-François AujolMathieu BrédifAurélie Bugeau
- 2018
Environmental Science, Engineering
This work promotes an alternative approach by using this image representation of the 3D point cloud, taking advantage of the fact that the problem of disocclusion has been intensively studied in the 2D image processing community over the past decade.
- 11
- PDF
- Bichen WuAlvin WanXiangyu YueK. Keutzer
- 2018
Computer Science, Engineering
2018 IEEE International Conference on Robotics…
An end-to-end pipeline called SqueezeSeg based on convolutional neural networks (CNN), which takes a transformed LiDAR point cloud as input and directly outputs a point-wise label map, which is then refined by a conditional random field (CRF) implemented as a recurrent layer.
- 729
- Highly Influential[PDF]
- Loic LandrieuM. Simonovsky
- 2018
Computer Science, Environmental Science
2018 IEEE/CVF Conference on Computer Vision and…
It is argued that the organization of 3D point clouds can be efficiently captured by a structure called superpoint graph (SPG), derived from a partition of the scanned scene into geometrically hom*ogeneous elements.
- 1,107 [PDF]
- Bichen WuXuanyu ZhouSicheng ZhaoXiangyu YueK. Keutzer
- 2019
Environmental Science, Computer Science
2019 International Conference on Robotics and…
This work introduces a new model SqueezeSegV2, which is more robust against dropout noises in LiDAR point cloud and therefore achieves significant accuracy improvement, and a domain-adaptation training pipeline consisting of three major components: learned intensity rendering, geodesic correlation alignment, and progressive domain calibration.
- 549
- Highly Influential[PDF]
- C. QiHao SuKaichun MoL. Guibas
- 2017
Computer Science
2017 IEEE Conference on Computer Vision and…
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
- 11,963 [PDF]
- Yin ZhouOncel Tuzel
- 2018
Computer Science, Engineering
2018 IEEE/CVF Conference on Computer Vision and…
VoxelNet is proposed, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network and learns an effective discriminative representation of objects with various geometries, leading to encouraging results in3D detection of pedestrians and cyclists.
- 3,112 [PDF]
- M. HimmelsbachA. MuellerT. LuettelH. Wuensche
- 2008
Engineering, Computer Science
A LIDAR-based perception system for ground robot mobility, consisting of 3D object detection, classification and tracking, enabling it to safely navigate in urban traffic-like scenarios as well as in off-road convoy scenarios.
- 154
- Chen FengYuichi TaguchiV. Kamat
- 2014
Computer Science, Engineering
2014 IEEE International Conference on Robotics…
The proposed algorithm can reliably detect all major planes in the scene at a frame rate of more than 35Hz for 640×480 point clouds, which to the best of the knowledge is much faster than state-of-the-art algorithms.
- 196
- PDF
- Loic LandrieuMohamed Boussaha
- 2019
Computer Science
2019 IEEE/CVF Conference on Computer Vision and…
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,…
- 139 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers