GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Qijun, Xing, Zhen, Wu, Zuxuan, Jiang, Yu-Gang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914998903635968
author Feng, Qijun
Xing, Zhen
Wu, Zuxuan
Jiang, Yu-Gang
author_facet Feng, Qijun
Xing, Zhen
Wu, Zuxuan
Jiang, Yu-Gang
contents We introduce GeoGS3D, a novel two-stage framework for reconstructing detailed 3D objects from single-view images. Inspired by the success of pre-trained 2D diffusion models, our method incorporates an orthogonal plane decomposition mechanism to extract 3D geometric features from the 2D input, facilitating the generation of multi-view consistent images. During the following Gaussian Splatting, these images are fused with epipolar attention, fully utilizing the geometric correlations across views. Moreover, we propose a novel metric, Gaussian Divergence Significance (GDS), to prune unnecessary operations during optimization, significantly accelerating the reconstruction process. Extensive experiments demonstrate that GeoGS3D generates images with high consistency across views and reconstructs high-quality 3D objects, both qualitatively and quantitatively.
format Preprint
id arxiv_https___arxiv_org_abs_2403_10242
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting
Feng, Qijun
Xing, Zhen
Wu, Zuxuan
Jiang, Yu-Gang
Computer Vision and Pattern Recognition
We introduce GeoGS3D, a novel two-stage framework for reconstructing detailed 3D objects from single-view images. Inspired by the success of pre-trained 2D diffusion models, our method incorporates an orthogonal plane decomposition mechanism to extract 3D geometric features from the 2D input, facilitating the generation of multi-view consistent images. During the following Gaussian Splatting, these images are fused with epipolar attention, fully utilizing the geometric correlations across views. Moreover, we propose a novel metric, Gaussian Divergence Significance (GDS), to prune unnecessary operations during optimization, significantly accelerating the reconstruction process. Extensive experiments demonstrate that GeoGS3D generates images with high consistency across views and reconstructs high-quality 3D objects, both qualitatively and quantitatively.
title GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.10242