Pose-free 3D Gaussian splatting via shape-ray estimation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Na, Youngju, Kim, Taeyeon, Lee, Jumin, Han, Kyu Beom, Kim, Woo Jae, Yoon, Sung-eui
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914104712626176
author Na, Youngju
Kim, Taeyeon
Lee, Jumin
Han, Kyu Beom
Kim, Woo Jae
Yoon, Sung-eui
author_facet Na, Youngju
Kim, Taeyeon
Lee, Jumin
Han, Kyu Beom
Kim, Woo Jae
Yoon, Sung-eui
contents While generalizable 3D Gaussian splatting enables efficient, high-quality rendering of unseen scenes, it heavily depends on precise camera poses for accurate geometry. In real-world scenarios, obtaining accurate poses is challenging, leading to noisy pose estimates and geometric misalignments. To address this, we introduce SHARE, a pose-free, feed-forward Gaussian splatting framework that overcomes these ambiguities by joint shape and camera rays estimation. Instead of relying on explicit 3D transformations, SHARE builds a pose-aware canonical volume representation that seamlessly integrates multi-view information, reducing misalignment caused by inaccurate pose estimates. Additionally, anchor-aligned Gaussian prediction enhances scene reconstruction by refining local geometry around coarse anchors, allowing for more precise Gaussian placement. Extensive experiments on diverse real-world datasets show that our method achieves robust performance in pose-free generalizable Gaussian splatting. Code is avilable at https://github.com/youngju-na/SHARE
format Preprint
id arxiv_https___arxiv_org_abs_2505_22978
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pose-free 3D Gaussian splatting via shape-ray estimation
Na, Youngju
Kim, Taeyeon
Lee, Jumin
Han, Kyu Beom
Kim, Woo Jae
Yoon, Sung-eui
Computer Vision and Pattern Recognition
While generalizable 3D Gaussian splatting enables efficient, high-quality rendering of unseen scenes, it heavily depends on precise camera poses for accurate geometry. In real-world scenarios, obtaining accurate poses is challenging, leading to noisy pose estimates and geometric misalignments. To address this, we introduce SHARE, a pose-free, feed-forward Gaussian splatting framework that overcomes these ambiguities by joint shape and camera rays estimation. Instead of relying on explicit 3D transformations, SHARE builds a pose-aware canonical volume representation that seamlessly integrates multi-view information, reducing misalignment caused by inaccurate pose estimates. Additionally, anchor-aligned Gaussian prediction enhances scene reconstruction by refining local geometry around coarse anchors, allowing for more precise Gaussian placement. Extensive experiments on diverse real-world datasets show that our method achieves robust performance in pose-free generalizable Gaussian splatting. Code is avilable at https://github.com/youngju-na/SHARE
title Pose-free 3D Gaussian splatting via shape-ray estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.22978