CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

• URL: http://arxiv.org/abs/2008.02792v2
• Date: Wed, 11 Nov 2020 19:00:31 GMT
• Title: CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
• Authors: Davis Rempe, Tolga Birdal, Yongheng Zhao, Zan Gojcic, Srinath Sridhar, Leonidas J. Guibas
• Abstract summary: We propose a method to learn object Canonical Point Cloud Representations of dynamically or moving objects. We demonstrate the effectiveness of our method on several applications including shape reconstruction, camera pose estimation, continuoustemporal sequence reconstruction, and correspondence estimation.
• Score: 72.4716073597902
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects. Our goal is to enable information aggregation over time and the interrogation of object state at any spatiotemporal neighborhood in the past, observed or not. Different from previous work, CaSPR learns representations that support spacetime continuity, are robust to variable and irregularly spacetime-sampled point clouds, and generalize to unseen object instances. Our approach divides the problem into two subtasks. First, we explicitly encode time by mapping an input point cloud sequence to a spatiotemporally-canonicalized object space. We then leverage this canonicalization to learn a spatiotemporal latent representation using neural ordinary differential equations and a generative model of dynamically evolving shapes using continuous normalizing flows. We demonstrate the effectiveness of our method on several applications including shape reconstruction, camera pose estimation, continuous spatiotemporal sequence reconstruction, and correspondence estimation from irregularly or intermittently sampled observations.

Related papers

• TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes [63.95928298690001]
  We present TPP-Gaze, a novel and principled approach to model scanpath dynamics based on Neural Temporal Point Process (TPP) Our results show the overall superior performance of the proposed model compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-10-30T19:22:38Z)
• Surgformer: Surgical Transformer with Hierarchical Temporal Attention for Surgical Phase Recognition [7.682613953680041]
  We propose the Surgical Transformer (Surgformer) to address the issues of spatial-temporal modeling and redundancy in an end-to-end manner. We show that our proposed Surgformer performs favorably against the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-08-07T16:16:31Z)
• Space and Time Continuous Physics Simulation From Partial Observations [0.0]
  Data-driven methods based on large-scale machine learning promise high adaptivity by integrating long-range dependencies more directly and efficiently. We focus on fluid dynamics and address the shortcomings of a large part of the literature, which are based on fixed support for computations and predictions in the form of regular or irregular grids. We propose a novel setup to perform predictions in a continuous spatial and temporal domain while being trained on sparse observations.
  arXiv  Detail & Related papers  (2024-01-17T13:24:04Z)
• Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking [52.393359791978035]
  Motion2VecSets is a 4D diffusion model for dynamic surface reconstruction from point cloud sequences. We parameterize 4D dynamics with latent sets instead of using global latent codes. For more temporally-coherent object tracking, we synchronously denoise deformation latent sets and exchange information across multiple frames.
  arXiv  Detail & Related papers  (2024-01-12T15:05:08Z)
• Spatio-Temporal Branching for Motion Prediction using Motion Increments [55.68088298632865]
  Human motion prediction (HMP) has emerged as a popular research topic due to its diverse applications. Traditional methods rely on hand-crafted features and machine learning techniques. We propose a noveltemporal-temporal branching network using incremental information for HMP.
  arXiv  Detail & Related papers  (2023-08-02T12:04:28Z)
• PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences [51.53563462897779]
  We propose a point-ordered (PST) convolution to achieve informative representations of point cloud sequences. PST first disentangles space and time in point cloud sequences, then a spatial convolution is employed to capture local structure points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension. We incorporate the proposed PST convolution into a deep network, namely PSTNet, to extract features of point cloud sequences in a hierarchical manner.
  arXiv  Detail & Related papers  (2022-05-27T02:14:43Z)
• TPCN: Temporal Point Cloud Networks for Motion Forecasting [47.829152433166016]
  We propose a novel framework with joint spatial and temporal learning for trajectory prediction. In the spatial dimension, agents can be viewed as an unordered point set, and thus it is straightforward to apply point cloud learning techniques to model agents' locations. Experiments on the Argoverse motion forecasting benchmark show that our approach achieves the state-of-the-art results.
  arXiv  Detail & Related papers  (2021-03-04T14:44:32Z)
• Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds [16.019588704177288]
  Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets. We present a novel method that takes advantage of current deep learning techniques for unsupervised learning of global registration from a temporal sequence of point clouds.
  arXiv  Detail & Related papers  (2020-06-17T06:00:36Z)
• Dynamic Point Cloud Denoising via Manifold-to-Manifold Distance [24.174744253496513]
  We represent dynamic point clouds naturally on spatial-temporal graphs, and exploit the temporal consistency with respect to the underlying surface (manifold) We formulate dynamic point cloud denoising as the joint optimization of the desired point cloud and underlying graph representation. Experimental results show that the proposed method significantly outperforms independent denoising of each frame from state-of-the-art static point cloud denoising approaches.
  arXiv  Detail & Related papers  (2020-03-17T04:54:20Z)

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.