LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
Recent large reconstruction models have made notable progress in generating high-quality 3D objects from single images. However, current reconstruction methods often rely on explicit camera pose estimation or fixed viewpoints, restricting their flexibility and practical applicability. We reformulate 3D reconstruction as image-to-image translation and introduce the Relative Coordinate Map (RCM), which aligns multiple unposed images to a ''main'' view without pose estimation. While RCM simplifies the process, its lack of global 3D supervision can yield noisy outputs. To address this, we propose Relative Coordinate Gaussians (RCG) as an extension to RCM, which treats each pixel's coordinates as a Gaussian center and employs differentiable rasterization for consistent geometry and pose recovery. Our LucidFusion framework handles an arbitrary number of unposed inputs, producing robust 3D reconstructions within seconds and paving the way for more flexible, pose-free 3D pipelines.
Description
CCS Concepts: Computing methodologies → 3D imaging; Reconstruction
@article{10.1111:cgf.70227,
journal = {Computer Graphics Forum},
title = {{LucidFusion: Reconstructing 3D Gaussians with Arbitrary Unposed Images}},
author = {He, Hao and Liang, Yixun and Wang, Luozhou and Cai, Yuanhao and Xu, Xinli and Guo, Haoxiang and Wen, Xiang and Chen, Yingcong},
year = {2025},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70227}
}