ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting
Ruijie Zhu, Mulin Yu, Linning Xu, Lihan Jiang, Yixuan Li, Tianzhu Zhang, Jiangmiao Pang, Bo Dai
3D Gaussian Splatting以其高保真重建和实时新颖的观点合成而闻名,但其缺乏语义理解限制了对象级感知。 在这项工作中,我们提出了ObjectGS,一个对象感知框架,将3D场景重建与语义理解统一。 ObjectGS没有将场景视为一个统一的整体,而是将单个对象建模为生成神经高斯并共享对象ID的本地锚,从而实现精确的对象级重建。 在训练过程中,我们动态地生长或修剪这些锚并优化它们的特征,而带有分类损失的一次性ID编码可以强制执行明确的语义约束。 我们通过广泛的实验表明,ObjectGS不仅在开放词汇和泛光分割任务方面优于最先进的方法,而且还与网格提取和场景编辑等应用程序无缝集成。 项目页面:https://ruijiezhu94.github.io/ObjectGS_page
3D Gaussian Splatting is renowned for its high-fidelity reconstructions and real-time novel view synthesis, yet its lack of semantic understanding limits object-level perception. In this work, we propose ObjectGS, an object-aware framework that unifies 3D scene reconstruction with semantic understanding. Instead of treating the scene as a unified whole, ObjectGS models individual objects as local anchors that generate neural Gaussians and share object IDs, enabling precise object-level reconstru...