Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wei, Dongxu, Li, Zhiqi, Liu, Peidong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929733495685120
author Wei, Dongxu
Li, Zhiqi
Liu, Peidong
author_facet Wei, Dongxu
Li, Zhiqi
Liu, Peidong
contents Prior works employing pixel-based Gaussian representation have demonstrated efficacy in feed-forward sparse-view reconstruction. However, such representation necessitates cross-view overlap for accurate depth estimation, and is challenged by object occlusions and frustum truncations. As a result, these methods require scene-centric data acquisition to maintain cross-view overlap and complete scene visibility to circumvent occlusions and truncations, which limits their applicability to scene-centric reconstruction. In contrast, in autonomous driving scenarios, a more practical paradigm is ego-centric reconstruction, which is characterized by minimal cross-view overlap and frequent occlusions and truncations. The limitations of pixel-based representation thus hinder the utility of prior works in this task. In light of this, this paper conducts an in-depth analysis of different representations, and introduces Omni-Gaussian representation with tailored network design to complement their strengths and mitigate their drawbacks. Experiments show that our method significantly surpasses state-of-the-art methods, pixelSplat and MVSplat, in ego-centric reconstruction, and achieves comparable performance to prior works in scene-centric reconstruction.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06273
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction
Wei, Dongxu
Li, Zhiqi
Liu, Peidong
Computer Vision and Pattern Recognition
Graphics
Prior works employing pixel-based Gaussian representation have demonstrated efficacy in feed-forward sparse-view reconstruction. However, such representation necessitates cross-view overlap for accurate depth estimation, and is challenged by object occlusions and frustum truncations. As a result, these methods require scene-centric data acquisition to maintain cross-view overlap and complete scene visibility to circumvent occlusions and truncations, which limits their applicability to scene-centric reconstruction. In contrast, in autonomous driving scenarios, a more practical paradigm is ego-centric reconstruction, which is characterized by minimal cross-view overlap and frequent occlusions and truncations. The limitations of pixel-based representation thus hinder the utility of prior works in this task. In light of this, this paper conducts an in-depth analysis of different representations, and introduces Omni-Gaussian representation with tailored network design to complement their strengths and mitigate their drawbacks. Experiments show that our method significantly surpasses state-of-the-art methods, pixelSplat and MVSplat, in ego-centric reconstruction, and achieves comparable performance to prior works in scene-centric reconstruction.
title Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2412.06273