Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark

Häckel, Timo; Savinov, Nikolay; Ladický, Ľubor; Wegner, Jan Dirk; Schindler, Konrad; Pollefeys, Marc

doi:10.48550/arxiv.1704.03847

Cited by 56 publications

(109 citation statements)

References 0 publications

Supporting

Mentioning

109

Contrasting

Order By: Relevance

“…In order to evaluate the performance of potential convolution, we conduct experiments on several widely used datasets, ModelNet40 [44], ShapeNet [47], Seman-tic3D [11] and S3DIS [1]. To more fairly compare the effectiveness of our methods, we do not attempt to design a special network structure for potential convolution, but reuse the popular networks proposed by other related methods and plug in our potential convolution to the basic framework or replace the original point convolution with ours.…”

Section: Methodsmentioning

confidence: 99%

Potential Convolution: Embedding Point Clouds into Potential Fields

Chen,

Deng,

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, various convolutions based on continuous or discrete kernels for point cloud processing have been widely studied, and achieve impressive performance in many applications, such as shape classification, scene segmentation and so on. However, they still suffer from some drawbacks. For continuous kernels, the inaccurate estimation of the kernel weights constitutes a bottleneck for further improving the performance; while for discrete ones, the kernels represented as the points located in the 3D space are lack of rich geometry information. In this work, rather than defining a continuous or discrete kernel, we directly embed convolutional kernels into the learnable potential fields, giving rise to potential convolution. It is convenient for us to define various potential functions for potential convolution which can generalize well to a wide range of tasks. Specifically, we provide two simple yet effective potential functions via point-wise convolution operations. Comprehensive experiments demonstrate the effectiveness of our method, which achieves superior performance on the popular 3D shape classification and scene segmentation benchmarks compared with other state-of-the-art point convolution methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Potential Convolution: Embedding Point Clouds into Potential Fields

Chen,

Deng,

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…This is very different from the dense point clouds of mapping systems such as Toronto-3D [6] or our Paris-CARLA-3D dataset. For the semantic segmentation and scene completion tasks, SemanticKITTI [7] uses only one single LiDAR scan as input (one rotation of the LiDAR). In our dataset, we wish to find the semantic and seek to complete the "holes" on the dense point cloud after the accumulation of all LiDAR scans.…”

Section: Related Datasetsmentioning

confidence: 99%

“…Moreover, larger occluded areas are present in outdoor scenes, caused by static and temporary foreground objects, such as trees, parked vehicles, bus stops, and benches. SemanticKITTI [7] is a dataset conducting scene completion (SC) and semantic scene completion (SSC) on LiDAR data, but they use only one single scan as input, with a target (ground truth) being the accumulation of all LiDAR scans. In our dataset, we seek to complete the "holes" from the accumulation of all LiDAR scans.…”

Section: Scene Completion (Sc) Taskmentioning

confidence: 99%

Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mapping

et al. 2021

View full text Add to dashboard Cite

Paris-CARLA-3D is a dataset of several dense colored point clouds of outdoor environments built by a mobile LiDAR and camera system. The data are composed of two sets with synthetic data from the open source CARLA simulator (700 million points) and real data acquired in the city of Paris (60 million points), hence the name Paris-CARLA-3D. One of the advantages of this dataset is to have simulated the same LiDAR and camera platform in the open source CARLA simulator as the one used to produce the real data. In addition, manual annotation of the classes using the semantic tags of CARLA was performed on the real data, allowing the testing of transfer methods from the synthetic to the real data. The objective of this dataset is to provide a challenging dataset to evaluate and improve methods on difficult vision tasks for the 3D mapping of outdoor environments: semantic segmentation, instance segmentation, and scene completion. For each task, we describe the evaluation protocol as well as the experiments carried out to establish a baseline.

show abstract

“…With the continuous advancement of range sensors, such as depth cameras and LIDAR, more and more 3D point clouds are captured and processed in many different applications, including automated driving [19], human-computer interactions [13] and augmented reality [40]. Recently, deep neural networks have exhibited excellent performance in supervised tasks on point clouds, such as classification [23,10], segmentation [18,37,31] and registration [3,33,8]. In the supervised learning scheme, manual labeling of a large amount of point clouds is needed for model training.…”

Section: Introductionmentioning

confidence: 99%

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

Luo,

Liu,

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep neural networks have achieved promising performance in supervised point cloud applications, but manual annotation is extremely expensive and time-consuming in supervised learning schemes. Unsupervised domain adaptation (UDA) addresses this problem by training a model with only labeled data in the source domain but making the model generalize well in the target domain. Existing studies show that self-supervised learning using both source and target domain data can help improve the adaptability of trained models, but they all rely on hand-crafted designs of the self-supervised tasks. In this paper, we propose a learnable self-supervised task and integrate it into a selfsupervision-based point cloud UDA architecture. Specifically, we propose a learnable nonlinear transformation that transforms a part of a point cloud to generate abundant and complicated point clouds while retaining the original semantic information, and the proposed self-supervised task is to reconstruct the original point cloud from the transformed ones. In the UDA architecture, an encoder is shared between the networks for the self-supervised task and the main task of point cloud classification or segmentation, so that the encoder can be trained to extract features suitable for both the source and the target domain data. Experiments on PointDA-10 and PointSegDA datasets show that the proposed method achieves new state-of-the-art performance on both classification and segmentation tasks of point cloud UDA. Code will be made publicly available.

show abstract

Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark

Cited by 56 publications

References 0 publications

Potential Convolution: Embedding Point Clouds into Potential Fields

Potential Convolution: Embedding Point Clouds into Potential Fields

Paris-CARLA-3D: A Real and Synthetic Outdoor Point Cloud Dataset for Challenging Tasks in 3D Mapping

A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds

Contact Info

Product

Resources

About