arXiv (Cornell University) · 2019 · 13 citations · 9 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDeep LearningFeature DescriptionPoint Cloud ProcessingRepresentation LearningShape RepresentationUnsupervised LearningDeep Feature LearningEmbedding LearningLatent Space EmbeddingLatent Space ModelsLearned Feature EmbeddingsPoint Cloud RepresentationPoint Cloud Representation LearningUnsupervised Feature Learning
We present a novel approach to learning a point-wise, meaningful embedding for point-clouds in an unsupervised manner, through the use of neural-networks. The domain of point-cloud processing via neural-networks is rapidly evolving, with novel architectures and applications frequently emerging. Within this field of research, the availability and plethora of unlabeled point-clouds as well as their possible applications make finding ways of characterizing this type of data appealing. Though significant advancement was achieved in the realm of unsupervised learning, its adaptation to the point-cloud representation is not trivial. Previous research focuses on the embedding of entire point-clouds representing an object in a meaningful manner. We present a deep learning framework to learn point-wise description from a set of shapes without supervision. Our approach leverages self-supervision to define a relevant loss function to learn rich per-point features. We train a neural-network with objectives based on context derived directly from the raw data, with no added annotation. We use local structures of point-clouds to incorporate geometric information into each point's latent representation. In addition to using local geometric information, we encourage adjacent points to have similar representations and vice-versa, creating a smoother, more descriptive representation. We demonstrate the ability of our method to capture meaningful point-wise features through three applications. By clustering the learned embedding space, we perform unsupervised part-segmentation on point clouds. By calculating euclidean distance in the latent space we derive semantic point-analogies. Finally, by retrieving nearest-neighbors in our learned latent space we present meaningful point-correspondence within and among point-clouds.
9
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Raffaelli Charles, Hao Su, Kaichun Mo et al. · 2017 · 9.8K citations
Dynamic Graph CNN for Learning on Point Clouds
Yue Wang, Yongbin Sun, Ziwei Liu et al. · ACM Transactions on Graphics · 2019 · 6.7K citations · Full text
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
Yaoqing Yang, Chen Feng, Yiru Shen et al. · 2018 · 1.4K citations
A scalable active framework for region annotation in 3D shape collections
Li Yi, Vladimir G. Kim, Duygu Ceylan et al. · ACM Transactions on Graphics · 2016 · 1.3K citations