MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Wangze, Gao, Huachen, Shen, Shihe, Peng, Rui, Jiao, Jianbo, Wang, Ronggang
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912039972110336
author Xu, Wangze
Gao, Huachen
Shen, Shihe
Peng, Rui
Jiao, Jianbo
Wang, Ronggang
author_facet Xu, Wangze
Gao, Huachen
Shen, Shihe
Peng, Rui
Jiao, Jianbo
Wang, Ronggang
contents Recently, the Neural Radiance Field (NeRF) advancement has facilitated few-shot Novel View Synthesis (NVS), which is a significant challenge in 3D vision applications. Despite numerous attempts to reduce the dense input requirement in NeRF, it still suffers from time-consumed training and rendering processes. More recently, 3D Gaussian Splatting (3DGS) achieves real-time high-quality rendering with an explicit point-based representation. However, similar to NeRF, it tends to overfit the train views for lack of constraints. In this paper, we propose \textbf{MVPGS}, a few-shot NVS method that excavates the multi-view priors based on 3D Gaussian Splatting. We leverage the recent learning-based Multi-view Stereo (MVS) to enhance the quality of geometric initialization for 3DGS. To mitigate overfitting, we propose a forward-warping method for additional appearance constraints conforming to scenes based on the computed geometry. Furthermore, we introduce a view-consistent geometry constraint for Gaussian parameters to facilitate proper optimization convergence and utilize a monocular depth regularization as compensation. Experiments show that the proposed method achieves state-of-the-art performance with real-time rendering speed. Project page: https://zezeaaa.github.io/projects/MVPGS/
format Preprint
id arxiv_https___arxiv_org_abs_2409_14316
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views
Xu, Wangze
Gao, Huachen
Shen, Shihe
Peng, Rui
Jiao, Jianbo
Wang, Ronggang
Computer Vision and Pattern Recognition
Recently, the Neural Radiance Field (NeRF) advancement has facilitated few-shot Novel View Synthesis (NVS), which is a significant challenge in 3D vision applications. Despite numerous attempts to reduce the dense input requirement in NeRF, it still suffers from time-consumed training and rendering processes. More recently, 3D Gaussian Splatting (3DGS) achieves real-time high-quality rendering with an explicit point-based representation. However, similar to NeRF, it tends to overfit the train views for lack of constraints. In this paper, we propose \textbf{MVPGS}, a few-shot NVS method that excavates the multi-view priors based on 3D Gaussian Splatting. We leverage the recent learning-based Multi-view Stereo (MVS) to enhance the quality of geometric initialization for 3DGS. To mitigate overfitting, we propose a forward-warping method for additional appearance constraints conforming to scenes based on the computed geometry. Furthermore, we introduce a view-consistent geometry constraint for Gaussian parameters to facilitate proper optimization convergence and utilize a monocular depth regularization as compensation. Experiments show that the proposed method achieves state-of-the-art performance with real-time rendering speed. Project page: https://zezeaaa.github.io/projects/MVPGS/
title MVPGS: Excavating Multi-view Priors for Gaussian Splatting from Sparse Input Views
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.14316