Lune

CVPR2025顶会

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

Dongxu Wei, Zhiqi Li, Peidong Liu

2025年份
14顶会引用

摘要

Input Views (real or synthetic) Novel Views Inference Rendering Reconstructed Scenes Figure 1. Provided with six surrounding images captured in real world or synthesized by 2D diffusion models, we can generate high-quality 3D Gaussians based on our Omni-Gaussian representation for ego-centric scene reconstruction and novel view synthesis.

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

lune papers fulltext b24a7159-17ce-4aa3-aaa3-5a9b9f22fc7d

引用它的顶会 Paper14

问问它们各自怎么用它

它引用的顶会 Paper29

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖