Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space

• URL: http://arxiv.org/abs/2207.04161v1
• Date: Sat, 9 Jul 2022 00:14:39 GMT
• Title: Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space
• Authors: Amine Ouasfi and Adnane Boukhayma
• Abstract summary: We explore a new idea for learning based shape reconstruction from a point cloud. We use a convolutional encoder to build a feature space given the input point cloud. An implicit decoder learns to predict signed distance values given points represented in this feature space.
• Score: 6.675491069288519
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We explore a new idea for learning based shape reconstruction from a point cloud, based on the recently popularized implicit neural shape representations. We cast the problem as a few-shot learning of implicit neural signed distance functions in feature space, that we approach using gradient based meta-learning. We use a convolutional encoder to build a feature space given the input point cloud. An implicit decoder learns to predict signed distance values given points represented in this feature space. Setting the input point cloud, i.e. samples from the target shape function's zero level set, as the support (i.e. context) in few-shot learning terms, we train the decoder such that it can adapt its weights to the underlying shape of this context with a few (5) tuning steps. We thus combine two types of implicit neural network conditioning mechanisms simultaneously for the first time, namely feature encoding and meta-learning. Our numerical and qualitative evaluation shows that in the context of implicit reconstruction from a sparse point cloud, our proposed strategy, i.e. meta-learning in feature space, outperforms existing alternatives, namely standard supervised learning in feature space, and meta-learning in euclidean space, while still providing fast inference.

Related papers

• Point Cloud Compression with Implicit Neural Representations: A Unified Framework [54.119415852585306]
  We present a pioneering point cloud compression framework capable of handling both geometry and attribute components. Our framework utilizes two coordinate-based neural networks to implicitly represent a voxelized point cloud. Our method exhibits high universality when contrasted with existing learning-based techniques.
  arXiv  Detail & Related papers  (2024-05-19T09:19:40Z)
• Clustering based Point Cloud Representation Learning for 3D Analysis [80.88995099442374]
  We propose a clustering based supervised learning scheme for point cloud analysis. Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space. Our algorithm shows notable improvements on famous point cloud segmentation datasets.
  arXiv  Detail & Related papers  (2023-07-27T03:42:12Z)
• PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning [72.07350827773442]
  We propose to solve open-set point cloud learning using a novel Point Cut-and-Mix mechanism. We use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage. The Unknown-Point Estimator module learns to exploit the point cloud's feature context for discriminating the known and unknown data.
  arXiv  Detail & Related papers  (2022-12-05T03:53:51Z)
• Upsampling Autoencoder for Self-Supervised Point Cloud Learning [11.19408173558718]
  We propose a self-supervised pretraining model for point cloud learning without human annotations. Upsampling operation encourages the network to capture both high-level semantic information and low-level geometric information of the point cloud. We find that our UAE outperforms previous state-of-the-art methods in shape classification, part segmentation and point cloud upsampling tasks.
  arXiv  Detail & Related papers  (2022-03-21T07:20:37Z)
• Point Cloud Pre-training by Mixing and Disentangling [35.18101910728478]
  Mixing and Disentangling (MD) is a self-supervised learning approach for point cloud pre-training. We show that the encoder + ours (MD) significantly surpasses that of the encoder trained from scratch and converges quickly. We hope this self-supervised learning attempt on point clouds can pave the way for reducing the deeply-learned model dependence on large-scale labeled data.
  arXiv  Detail & Related papers  (2021-09-01T15:52:18Z)
• DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation [45.768040873409824]
  DRINet serves as the basic network structure for dual-representation learning. Our network achieves state-of-the-art results for point cloud classification and segmentation tasks. For large-scale outdoor scenarios, our method outperforms state-of-the-art methods with a real-time inference speed of 62ms per frame.
  arXiv  Detail & Related papers  (2021-08-09T13:23:54Z)
• UPDesc: Unsupervised Point Descriptor Learning for Robust Registration [54.95201961399334]
  UPDesc is an unsupervised method to learn point descriptors for robust point cloud registration. We show that our learned descriptors yield superior performance over existing unsupervised methods.
  arXiv  Detail & Related papers  (2021-08-05T17:11:08Z)
• Point Cloud Registration using Representative Overlapping Points [10.843159482657303]
  We propose ROPNet, a new deep learning model using Representative Overlapping Points with discriminative features for registration. Specifically, we propose a context-guided module which uses an encoder to extract global features for predicting point overlap score. Experiments over ModelNet40 using noisy and partially overlapping point clouds show that the proposed method outperforms traditional and learning-based methods.
  arXiv  Detail & Related papers  (2021-07-06T12:52:22Z)
• Refinement of Predicted Missing Parts Enhance Point Cloud Completion [62.997667081978825]
  Point cloud completion is the task of predicting complete geometry from partial observations using a point set representation for a 3D shape. Previous approaches propose neural networks to directly estimate the whole point cloud through encoder-decoder models fed by the incomplete point set. This paper proposes an end-to-end neural network architecture that focuses on computing the missing geometry and merging the known input and the predicted point cloud.
  arXiv  Detail & Related papers  (2020-10-08T22:01:23Z)
• MetaSDF: Meta-learning Signed Distance Functions [85.81290552559817]
  Generalizing across shapes with neural implicit representations amounts to learning priors over the respective function space. We formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task.
  arXiv  Detail & Related papers  (2020-06-17T05:14:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.