Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis

• URL: http://arxiv.org/abs/2503.03132v1
• Date: Wed, 05 Mar 2025 03:02:59 GMT
• Title: Dynamic Neural Surfaces for Elastic 4D Shape Representation and Analysis
• Authors: Awais Nizamani, Hamid Laga, Guanjin Wang, Farid Boussaid, Mohammed Bennamoun, Anuj Srivastava,
• Abstract summary: We propose a framework for the statistical analysis of genus-zeroD surfaces that deform and evolve over time.<n>We introduce Dynamic Spherical Neural Surfaces (D-SNS), an efficient continuoustemporal representation for genus-0 4D surfaces.<n>We demonstrate the efficiency of the framework on 4D human and face datasets.
• Score: 36.228108480107906
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel framework for the statistical analysis of genus-zero 4D surfaces, i.e., 3D surfaces that deform and evolve over time. This problem is particularly challenging due to the arbitrary parameterizations of these surfaces and their varying deformation speeds, necessitating effective spatiotemporal registration. Traditionally, 4D surfaces are discretized, in space and time, before computing their spatiotemporal registrations, geodesics, and statistics. However, this approach may result in suboptimal solutions and, as we demonstrate in this paper, is not necessary. In contrast, we treat 4D surfaces as continuous functions in both space and time. We introduce Dynamic Spherical Neural Surfaces (D-SNS), an efficient smooth and continuous spatiotemporal representation for genus-0 4D surfaces. We then demonstrate how to perform core 4D shape analysis tasks such as spatiotemporal registration, geodesics computation, and mean 4D shape estimation, directly on these continuous representations without upfront discretization and meshing. By integrating neural representations with classical Riemannian geometry and statistical shape analysis techniques, we provide the building blocks for enabling full functional shape analysis. We demonstrate the efficiency of the framework on 4D human and face datasets. The source code and additional results are available at https://4d-dsns.github.io/DSNS/.

Related papers

• 4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives [116.2042238179433]
  In this paper, we frame dynamic scenes as unconstrained 4D volume learning problems.<n>We represent a target dynamic scene using a collection of 4D Gaussian primitives with explicit geometry and appearance features.<n>This approach can capture relevant information in space and time by fitting the underlying photorealistic-temporal volume.<n> Notably, our 4DGS model is the first solution that supports real-time rendering of high-resolution, novel views for complex dynamic scenes.
  arXiv  Detail & Related papers  (2024-12-30T05:30:26Z)
• Level-Set Parameters: Novel Representation for 3D Shape Analysis [70.23417107911567]
  Recent development of neural fields brings in level-set parameters from signed distance functions as a novel, continuous, and numerical representation of 3D shapes.<n>We establish correlations across different shapes by formulating them as a pseudo-normal distribution, and learn the distribution prior to the respective dataset.<n>We demonstrate the promise of the novel representations through applications in shape classification, retrieval, and 6D object pose estimation.
  arXiv  Detail & Related papers  (2024-12-18T04:50:19Z)
• A Riemannian Approach for Spatiotemporal Analysis and Generation of 4D Tree-shaped Structures [38.04447518666407]
  We present the first comprehensive approach for modeling and analyzingtemporal shape variability in tree-like 4D objects. Our key contribution is the representation of tree-like 3D shapes using Square Root Velocity Trees (SFT) This reduces the problem of modeling and analyzing 4D tree-like shapes to that of modeling and analyzing elastic trajectories in the SRVFT space.
  arXiv  Detail & Related papers  (2024-08-22T14:39:30Z)
• SLS4D: Sparse Latent Space for 4D Novel View Synthesis [13.73892118198658]
  Existing dynamic NeRFs usually exploit a locally dense grid to fit the deformation field. We observe that the 4D space is inherently sparse. We propose to represent the 4D scene using a learnable sparse latent space, a.k.a. SLS4D.
  arXiv  Detail & Related papers  (2023-12-15T12:31:20Z)
• Geometry-Informed Neural Operator for Large-Scale 3D PDEs [76.06115572844882]
  We propose the geometry-informed neural operator (GINO) to learn the solution operator of large-scale partial differential equations. We successfully trained GINO to predict the pressure on car surfaces using only five hundred data points.
  arXiv  Detail & Related papers  (2023-09-01T16:59:21Z)
• LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling [69.56581851211841]
  We propose a novel Local 4D implicit Representation for Dynamic clothed human, named LoRD. Our key insight is to encourage the network to learn the latent codes of local part-level representation. LoRD has strong capability for representing 4D human, and outperforms state-of-the-art methods on practical applications.
  arXiv  Detail & Related papers  (2022-08-18T03:49:44Z)
• H4D: Human 4D Modeling by Learning Neural Compositional Representation [75.34798886466311]
  This work presents a novel framework that can effectively learn a compact and compositional representation for dynamic human. A simple yet effective linear motion model is proposed to provide a rough and regularized motion estimation. Experiments demonstrate our method is not only efficacy in recovering dynamic human with accurate motion and detailed geometry, but also amenable to various 4D human related tasks.
  arXiv  Detail & Related papers  (2022-03-02T17:10:49Z)
• 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface [7.637832293935966]
  We introduce 4DComplete, a novel data-driven approach that estimates the non-rigid motion for the unobserved geometry. For network training, we constructed a large-scale synthetic dataset called DeformingThings4D.
  arXiv  Detail & Related papers  (2021-05-05T07:39:12Z)
• 4D Atlas: Statistical Analysis of the Spatiotemporal Variability in Longitudinal 3D Shape Data [34.21760947722201]
  We propose a framework to learn a novel variability in 3D shape data sets, which contain observations of that subjects and deform over time. We treat a 3D surface as a point in a shape space equipped with an elastic metric that measures amount of bending and stretching that surfaces undergo. A 4D surface can then be seen as a trajectory in this space.
  arXiv  Detail & Related papers  (2021-01-23T02:59:55Z)

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.