Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Junyi, Tao, Jiachen, Wang, Haoxuan, Liu, Gaowen, Kompella, Ramana Rao, Yan, Yan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912612206247936
author Wu, Junyi
Tao, Jiachen
Wang, Haoxuan
Liu, Gaowen
Kompella, Ramana Rao
Yan, Yan
author_facet Wu, Junyi
Tao, Jiachen
Wang, Haoxuan
Liu, Gaowen
Kompella, Ramana Rao
Yan, Yan
contents We present Orientation-anchored Gaussian Splatting (OriGS), a novel framework for high-quality 4D reconstruction from casually captured monocular videos. While recent advances extend 3D Gaussian Splatting to dynamic scenes via various motion anchors, such as graph nodes or spline control points, they often rely on low-rank assumptions and fall short in modeling complex, region-specific deformations inherent to unconstrained dynamics. OriGS addresses this by introducing a hyperdimensional representation grounded in scene orientation. We first estimate a Global Orientation Field that propagates principal forward directions across space and time, serving as stable structural guidance for dynamic modeling. Built upon this, we propose Orientation-aware Hyper-Gaussian, a unified formulation that embeds time, space, geometry, and orientation into a coherent probabilistic state. This enables inferring region-specific deformation through principled conditioned slicing, adaptively capturing diverse local dynamics in alignment with global motion intent. Experiments demonstrate the superior reconstruction fidelity of OriGS over mainstream methods in challenging real-world dynamic scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23492
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
Wu, Junyi
Tao, Jiachen
Wang, Haoxuan
Liu, Gaowen
Kompella, Ramana Rao
Yan, Yan
Computer Vision and Pattern Recognition
We present Orientation-anchored Gaussian Splatting (OriGS), a novel framework for high-quality 4D reconstruction from casually captured monocular videos. While recent advances extend 3D Gaussian Splatting to dynamic scenes via various motion anchors, such as graph nodes or spline control points, they often rely on low-rank assumptions and fall short in modeling complex, region-specific deformations inherent to unconstrained dynamics. OriGS addresses this by introducing a hyperdimensional representation grounded in scene orientation. We first estimate a Global Orientation Field that propagates principal forward directions across space and time, serving as stable structural guidance for dynamic modeling. Built upon this, we propose Orientation-aware Hyper-Gaussian, a unified formulation that embeds time, space, geometry, and orientation into a coherent probabilistic state. This enables inferring region-specific deformation through principled conditioned slicing, adaptively capturing diverse local dynamics in alignment with global motion intent. Experiments demonstrate the superior reconstruction fidelity of OriGS over mainstream methods in challenging real-world dynamic scenes.
title Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.23492