NF3DM: Combining Neural Fields and Deformation Models for 3D Non-Rigid Motion Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Merrouche, Aymen, Wuhrer, Stefanie, Boyer, Edmond
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912575124406272
author Merrouche, Aymen
Wuhrer, Stefanie
Boyer, Edmond
author_facet Merrouche, Aymen
Wuhrer, Stefanie
Boyer, Edmond
contents We introduce a novel, data-driven approach for reconstructing temporally coherent 3D motion from unstructured and potentially partial observations of non-rigidly deforming shapes. Our goal is to achieve high-fidelity motion reconstructions for shapes that undergo near-isometric deformations, such as humans wearing loose clothing. The key novelty of our work lies in its ability to combine implicit shape representations with explicit mesh-based deformation models, enabling detailed and temporally coherent motion reconstructions without relying on parametric shape models or decoupling shape and motion. Each frame is represented as a neural field decoded from a feature space where observations over time are fused, hence preserving geometric details present in the input data. Temporal coherence is enforced with a near-isometric deformation constraint between adjacent frames that applies to the underlying surface in the neural field. Our method outperforms state-of-the-art approaches, as demonstrated by its application to human and animal motion sequences reconstructed from monocular depth videos.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08511
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NF3DM: Combining Neural Fields and Deformation Models for 3D Non-Rigid Motion Reconstruction
Merrouche, Aymen
Wuhrer, Stefanie
Boyer, Edmond
Computer Vision and Pattern Recognition
We introduce a novel, data-driven approach for reconstructing temporally coherent 3D motion from unstructured and potentially partial observations of non-rigidly deforming shapes. Our goal is to achieve high-fidelity motion reconstructions for shapes that undergo near-isometric deformations, such as humans wearing loose clothing. The key novelty of our work lies in its ability to combine implicit shape representations with explicit mesh-based deformation models, enabling detailed and temporally coherent motion reconstructions without relying on parametric shape models or decoupling shape and motion. Each frame is represented as a neural field decoded from a feature space where observations over time are fused, hence preserving geometric details present in the input data. Temporal coherence is enforced with a near-isometric deformation constraint between adjacent frames that applies to the underlying surface in the neural field. Our method outperforms state-of-the-art approaches, as demonstrated by its application to human and animal motion sequences reconstructed from monocular depth videos.
title NF3DM: Combining Neural Fields and Deformation Models for 3D Non-Rigid Motion Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.08511