Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways

Tan, Wei; Qin, Nannan; Ma, Lingfei; Li, Ying; Du, Juan; Cai, Guorong; Yang, Ke; Li, Jonathan

doi:10.1109/cvprw50498.2020.00109

Cited by 180 publications

(93 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use the same network architecture for all the five largescale open datasets, Semantic3D [36], SemanticKITTI [3], Toronto-3D [37], NPM3D [73], S3DIS [72]. The Adam optimizer [74] with default parameters is applied.…”

Section: Methodsmentioning

confidence: 99%

“…In this section, we evaluate the semantic segmentation of our RandLA-Net on multiple large-scale public datasets: the outdoor Semantic3D [36], SemanticKITTI [3], Toronto-3D [37], NPM3D [73], and the indoor S3DIS [72]. For a fair comparison, we follow KPConv [23] to pre-process the whole input point clouds by using the grid-sampling strategy at the beginning.…”

Section: Semantic Segmentation On Benchmarksmentioning

confidence: 99%

“…Overall, being built on the principles of simple random sampling and an effective local feature aggregator, our efficient neural architecture, named RandLA-Net, not only is up to 200× faster than existing approaches on large-scale point clouds, but also surpasses the state-of-the-art semantic segmentation methods on Semantic3D [36], SemanticKITTI [3] and Toronto-3D [37] benchmarks. Figure 1 shows qualitative results of our approach.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

Yang

Xie

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

100

View full text Add to dashboard Cite

We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Comparative experiments show that our RandLA-Net can process 1 million points in a single pass up to 200× faster than existing approaches. Moreover, extensive experiments on five large-scale point cloud datasets, including Semantic3D, SemanticKITTI, Toronto3D, NPM3D and S3DIS, demonstrate the state-of-the-art semantic segmentation performance of our RandLA-Net.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Semantic Segmentation On Benchmarksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

Yang

Xie

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

100

View full text Add to dashboard Cite

show abstract

“…SemanticKITTI [14] is the latest version of the KITTI dataset for point cloud segmentation. Other recent outdoor datasets include Toronto-3D MLS [22] and TUM-MLS [23]. We also summarize the main properties of the above discussed outdoor datasets along other existing datasets in Table 3 of Section IV, where we also give detail of the proposed dataset for comparison.…”

Section: B Point Cloud Datasetsmentioning

confidence: 99%

Annotation Tool and Urban Dataset for 3D Point Cloud Semantic Segmentation

et al. 2021

View full text Add to dashboard Cite

Accurate semantic segmentation of unstructured 3D point clouds requires large amount of annotated training data for deep learning. However, there is currently no free specialized software available that can efficiently annotate large 3D point clouds. We fill this gap by introducing PC-Annotate-a public annotation tool for 3D point cloud research. The proposed tool not only enables systematic annotation with a variety of fundamental volumetric shapes, but also provides useful functionalities of point cloud registration and the generation of volumetric samples that can be readily consumed by contemporary deep learning point cloud models. We also introduce a large outdoor public dataset for 3D semantic segmentation. The proposed dataset, PC-Urban is collected in a civic setup with Ouster LiDAR and labeled with PC-Annotate. It has over 4.3 billion points covering 66K frames and 25 annotated classes. Finally, we provide baseline semantic segmentation results on PC-Urban for popular recent techniques. INDEX TERMS 3D point cloud, Point Cloud Dataset, Annotation tool, Semantic Segmentation, LiDAR.

show abstract

“…We evaluated the proposed method on two datasets, CSPC [38] and Toronto3D [39]. CSPC (Complex Scene Point Cloud dataset) is the most recent point cloud dataset for semantic segmentation of large-scale outdoor scenes, covering five urban and rural scenes where scene-1 shows a simple street, scene-2 shows a busy urban street, scene-3 shows a busy urban street at night, scene-4 shows a campus, and scene-5 shows a rural street.…”

Section: Experiments Designmentioning

confidence: 99%

Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation

Geng

Lü

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Semantic segmentation of LiDAR point clouds has implications in self-driving, robots, and augmented reality, among others. In this paper, we propose a Multi-Scale Attentive Aggregation Network (MSAAN) to achieve the global consistency of point cloud feature representation and super segmentation performance. First, upon a baseline encoder-decoder architecture for point cloud segmentation, namely, RandLA-Net, an attentive skip connection was proposed to replace the commonly used concatenation to balance the encoder and decoder features of the same scales. Second, a channel attentive enhancement module was introduced to the local attention enhancement module to boost the local feature discriminability and aggregate the local channel structure information. Third, we developed a multi-scale feature aggregation method to capture the global structure of a point cloud from both the encoder and the decoder. The experimental results reported that our MSAAN significantly outperformed state-of-the-art methods, i.e., at least 15.3% mIoU improvement for scene-2 of CSPC dataset, 5.2% for scene-5 of CSPC dataset, and 6.6% for Toronto3D dataset.

show abstract

Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways

Cited by 180 publications

References 24 publications

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling

Annotation Tool and Urban Dataset for 3D Point Cloud Semantic Segmentation

Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation

Contact Info

Product

Resources

About