.png){kind=icon}
返回
Uni-Fusion: Universal Continuous Mapping
.png){kind=icon}
OA
AI
DOI：10.1109/TRO.2024.3351548.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We present Uni-Fusion, a universal continuous mapping framework for surfaces, surface properties (color, infrared, etc.) and more (latent features in contrastive language-image pretraining (CLIP) embedding space, etc.). We propose the first universal implicit encoding model that supports encoding of both geometry and different types of properties (RGB, infrared, features, etc.) without requiring any training. Based on this, our framework divides the point cloud into regular grid voxels and generates a latent feature in each voxel to form a latent implicit map (LIM) for geometries and arbitrary properties. Then, by fusing a local LIM frame-wisely into a global LIM, an incremental reconstruction is achieved. Encoded with corresponding types of data, our LIM is capable of generating continuous surfaces, surface property fields, surface feature fields, and all other possible options. To demonstrate the capabilities of our model, we implement three applications: incremental reconstruction for surfaces and color, 2-D-to-3-D transfer of fabricated properties, and open-vocabulary scene understanding by creating a text CLIP feature field on surfaces. We evaluate Uni-Fusion by comparing it in corresponding applications, from which Uni-Fusion shows high-flexibility in various applications while performing best or being competitive.
Keyword:
Mapping
RGB-D perception
semantic scene understanding
universal mapping
期刊
IF:
10.5
论文数:
3.3K
被引数:
2.8W
机构
引用论文
Metabolism-directed structure optimization of benzimidazole-basedFrancisella tularensisenoyl-reductase (FabI) inhibitors.png)
Xenobiotica
OAAI
XenobioticaIF0
OAAI分享收藏Screening metal-organic frameworks for adsorption-driven osmotic heat engines via grand canonical Monte Carlo simulations and machine learning通过大典蒙特卡罗模拟和机器学习筛选用于吸附驱动的渗透热发动机的金属有机框架iScienceOAAI
iScienceIF0
OAAI分享收藏
查看更多内容