MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences

Liu, Xingyu; Yan, Mingyu; Bohg, Jeannette

doi:10.1109/iccv.2019.00934

Cited by 187 publications

(161 citation statements)

References 33 publications

(62 reference statements)

Supporting

Mentioning

153

Contrasting

Order By: Relevance

“…Extensive experiments on multiple benchmarks demonstrate the high efficiency and the stateof-the-art performance of our approach. It would be interesting to extend our framework for the end-to-end 3D instance segmentation on large-scale point clouds by drawing on the recent work [97] and also for the real-time dynamic point cloud processing [98]. We implement simple batch parallelisation.…”

Section: Discussionmentioning

confidence: 99%

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

Yang

Xie

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

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: Discussionmentioning

confidence: 99%

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

Yang

Xie

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…To verify the effectiveness of PointRNN on the tasks of motion part segmentation and motion attribute estimation, we design two baselines to replace the network backbone. To build baseline1, we adopt a slightly modified version of Liu et al [LYB19]. We merge the point cloud sequence into a single point cloud and feed it to a PointNet++ to extract features.…”

Section: Analysis Of the Effects Of Different Network Designsmentioning

confidence: 99%

Self‐Supervised Learning of Part Mobility from Point Cloud Sequence

Shi

Cao

Zhou

2021

Computer Graphics Forum

View full text Add to dashboard Cite

Part mobility analysis is a significant aspect required to achieve a functional understanding of 3D objects. It would be natural to obtain part mobility from the continuous part motion of 3D objects. In this study, we introduce a self-supervised method for segmenting motion parts and predicting their motion attributes from a point cloud sequence representing a dynamic object. To sufficiently utilize spatiotemporal information from the point cloud sequence, we generate trajectories by using correlations among successive frames of the sequence instead of directly processing the point clouds. We propose a novel neural network architecture called PointRNN to learn feature representations of trajectories along with their part rigid motions. We evaluate our method on various tasks including motion part segmentation, motion axis prediction and motion range estimation. The results demon strate that our method outperforms previous techniques on both synthetic and real datasets. Moreover, our method has the ability to generalize to new and unseen objects. It is important to emphasize that it is not required to know any prior shape structure, prior shape category information or shape orientation. To the best of our knowledge, this is the first study on deep learning to extract part mobility from point cloud sequence of a dynamic object.

show abstract

“…In addition, MeteorNet (Liu et al, 2019b) and ASTA3DCNNs (Wang et al, 2021b) focus on the feature learning of multi-frame point clouds (more than three frames), while ours focuses on the motion relationship between two frames.…”

Section: Related Workmentioning

confidence: 99%

SFGAN: Unsupervised Generative Adversarial Learning of 3D Scene Flow from the 3D Scene Self

Wang

Chaokang

Shen

et al. 2021

Preprint

View full text Add to dashboard Cite

3D scene flow presents the 3D motion of each point in the 3D space, which forms the fundamental 3D motion perception for autonomous driving and server robots. Although the RGBD camera or LiDAR capture discrete 3D points in space, the objects and motions usually are continuous in the macro world. That is, the objects keep themselves consistent as they flow from the current frame to the next frame. Based on this insight, the Generative Adversarial Networks (GAN) is utilized to self-learn 3D scene flow with no need for ground truth. The fake point cloud of the second frame is synthesized from the predicted scene flow and the point cloud of the first frame. The adversarial training of the generator and discriminator is realized through synthesizing indistinguishable fake point cloud and discriminating the real point cloud and the synthesized fake point cloud. The experiments on KITTI scene flow dataset show that our method realizes promising results without ground truth. Just like a human observing a real-world scene, the proposed approach is capable of determining the consistency of the scene at different moments in spite of the exact flow value of each point is unknown in advance. Corresponding author(s) Email: wanghesheng@sjtu.edu.cn

show abstract

MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences

Cited by 187 publications

References 33 publications

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

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

Self‐Supervised Learning of Part Mobility from Point Cloud Sequence

SFGAN: Unsupervised Generative Adversarial Learning of 3D Scene Flow from the 3D Scene Self

Contact Info

Product

Resources

About