PCT: Large-Scale 3d Point Cloud Representations Via Graph Inception Networks with Applications to Autonomous Driving

Chen, Siheng; Niu, Sufeng; Lan, Tian; Liu, Baoan

doi:10.1109/icip.2019.8803525

Cited by 34 publications

(17 citation statements)

References 23 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many tasks need to deal with large scale scenes such as autonomous driving and remote sensing. Approaches [10,22,23,35] have explored large-scale point cloud analysis. SPG [35] uses superpoint graph structure to tackle the challenge of semantic segmentation of millions of points.…”

Section: Large-scale Point Cloud Semantic Segmentationmentioning

confidence: 99%

“…SPG [35] uses superpoint graph structure to tackle the challenge of semantic segmentation of millions of points. In addition to this structured format of point clouds, Voxel-based representation has been applied to some networks [22,23] for large-scale semantic segmentation. However, these representations require a huge amount of computation.…”

Section: Large-scale Point Cloud Semantic Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Point Cloud Semantic Segmentation with Cross-Correction Features

Chong

Wen

2022

Preprint

View full text Add to dashboard Cite

Real time large scale point cloud segmentation is an important but challenging task for practical application like autonomous driving. Existing real time methods have achieved acceptance performance by aggregating local information. However, most of them only exploit local spatial information or local semantic information dependently, few considering the complementarity of both. In this paper, we propose a model named Spatial-Semantic Incorporation Network (SSI-Net) for real time large scale point cloud segmentation. A Spatial-Semantic Cross-correction (SSC) module is introduced in SSI-Net as a basic unit. High quality contextual features can be learned through SSC by correct and update semantic features using spatial cues, and vice verse. Adopting the plug-and-play SSC module, we design SSI-Net as an encoder-decoder architecture. To ensure efficiency, it also adopts a random sample based hierarchical network structure. Extensive experiments on several prevalent datasets demonstrate that our method can achieve state-of-the-art performance.

show abstract

Section: Large-scale Point Cloud Semantic Segmentationmentioning

confidence: 99%

Section: Large-scale Point Cloud Semantic Segmentationmentioning

confidence: 99%

Point Cloud Semantic Segmentation with Cross-Correction Features

Chong

Wen

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, both the geometric partition and superpoint graph construction are computationally expensive. The recent FCPN [32] and PCT [33] apply both voxel-based and point-based networks to process the massive point clouds. Based on the assumption that points are sampled from locally Euclidean surfaces, TangentConv [66] firstly projects the local surface on the tangent plane and then operates on the projected geometry.…”

Section: Related Workmentioning

confidence: 99%

“…However, the preprocessing steps are too computationally heavy to be deployed in real-time applications. Both FCPN [32] and PCT [33] combine voxelization and pointlevel networks to process massive point clouds. However, they still partition the point clouds into small blocks for learning, resulting in the overall performance being suboptimal.…”

Section: Introductionmentioning

confidence: 99%

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

“…Fig. 12 showed their GNN-based auto-encoder (GAE) [192], [193] to encode 3D point clouds into a limited number of latent variables. One of the benefits of the GAE is that it allows graph signal reconstruction from a limited number of latent variables without requiring additional metadata.…”

Section: B Applied Deep Neural Networkmentioning

confidence: 99%

Soft Delivery: Survey on A New Paradigm for Wireless and Mobile Multimedia Streaming

Fujihashi¹,

Koike‐Akino²,

Watanabe³

2021

Preprint

View full text Add to dashboard Cite

The increasing demand for video streaming services is the key driver of modern wireless and mobile communications. For robust and high-quality delivery of video content over wireless and mobile networks, the main challenge is sending image and video signals to single and multiple users over unstable and diverse channel environments. To this end, many studies have designed digital-based video delivery schemes, which mainly consist of a sequence of digital-based coding and transmission schemes. Although digital-based schemes perform well when the channel characteristics are known in advance, significant quality degradation, known as cliff and leveling effects, often occurs owing to the fluctuating channel characteristics. To prevent cliff and leveling effects irrespective of the channel characteristics of each user, a new paradigm for wireless and mobile video streaming has been proposed. Soft delivery schemes skip the digital operations of quantization and entropy and channel coding while directly mapping the power-assigned frequency-domain coefficients onto the transmission symbols. This modification is based on the fact that the pixel distortion due to communication noise is proportional to the magnitude of the noise, resulting in graceful quality improvement, wherein quality is improved gradually, according to the wireless channel quality without any cliff and leveling effects. Herein, we present a comprehensive summary of soft delivery schemes. First, we provide a brief introduction on wireless and mobile video streaming. Second, we discuss the issues associated with conventional digital-based video delivery schemes. Third, an overview of soft delivery is presented, and then the state of the art in soft delivery is summarized by considering energy compaction, power allocation, bandwidth utilization, and packet loss resilience. Finally, an excursion on the extensions needed for immersive content and future research directions are provided.

show abstract

PCT: Large-Scale 3d Point Cloud Representations Via Graph Inception Networks with Applications to Autonomous Driving

Cited by 34 publications

References 23 publications

Point Cloud Semantic Segmentation with Cross-Correction Features

Point Cloud Semantic Segmentation with Cross-Correction Features

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

Soft Delivery: Survey on A New Paradigm for Wireless and Mobile Multimedia Streaming

Contact Info

Product

Resources

About