We introduce ShelfGaussian, an open-vocabulary multi-modal Gaussian-based 3D scene understanding framework supervised by off-the-shelf vision foundation models (VFMs). Gaussian-based methods have demonstrated superior performance and computational efficiency across a wide range of scene understanding tasks. However, existing methods either model objects as closed-set semantic Gaussians supervised by annotated 3D labels, neglecting their rendering ability, or learn open-set Gaussian representations via purely 2D self-supervision, leading to degraded geometry and limited to camera-only settings. To fully exploit the potential of Gaussians, we propose a Multi-Modal Gaussian Transformer that enables Gaussians to query features from diverse sensor modalities, and a Shelf-Supervised Learning Paradigm that efficiently optimizes Gaussians with VFM features jointly at 2D image and 3D scene levels. We evaluate ShelfGaussian on various perception and planning tasks. Experiments on Occ3D-nuScenes demonstrate its state-of-the-art zero-shot semantic occupancy prediction performance. ShelfGaussian is further evaluated on an unmanned ground vehicle (UGV) to assess its in the-wild performance across diverse urban scenarios. Project website: https://lunarlab-gatech.github.io/ShelfGaussian/.

翻译：我们提出ShelfGaussian，一个基于高斯表示、由现成视觉基础模型监督的开放词汇多模态三维场景理解框架。基于高斯的方法在各类场景理解任务中展现出卓越的性能与计算效率。然而，现有方法要么将目标建模为受标注三维标签监督的封闭语义高斯体，从而忽略其渲染能力；要么通过纯二维自监督学习开放集高斯表征，导致几何退化且局限于仅相机模式。为充分挖掘高斯体的潜力，我们提出多模态高斯变换器，使高斯体能够从不同传感器模态中查询特征；同时提出货架监督学习范式，在二维图像和三维场景层级联合利用视觉基础模型特征高效优化高斯体。我们在多种感知与规划任务上评估ShelfGaussian。在Occ3D-nuScenes数据集上的实验表明，该方法在零样本语义占据预测任务中达到最先进性能。ShelfGaussian还进一步在无人地面车辆上评估了其在多样城市场景中的野外性能。项目网站：https://lunarlab-gatech.github.io/ShelfGaussian/。