用现成视觉模型监督，让3D高斯点云实现开集语义理解。
ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding
- 多模态高斯变换器融合不同传感器特征，提升表达能力。
- 在Occ3D-nuScenes上零样本语义占据预测达最新水平。
- 适合需要真实场景泛化能力的机器人感知任务。
我们提出ShelfGaussian，一种基于高斯的开放词汇多模态3D场景理解框架，利用现成的视觉基础模型（VFMs）进行监督。高斯方法在多种场景理解任务中表现出卓越性能与计算效率。然而，现有方法或依赖标注3D标签建模封闭集语义高斯，忽略其渲染能力；或仅通过2D自监督学习开放集高斯表示，导致几何退化且局限于仅摄像头场景。为充分发挥高斯潜力，我们提出多模态高斯变压器，使高斯能查询多元传感器特征，并设计货架式监督范式，在2D图像与3D场景层面联合优化高斯特征。我们在多个感知与规划任务上评估ShelfGaussian。在Occ3D-nuScenes上的实验表明其零样本语义占据预测性能达到当前最优。进一步在无人地面车辆（UGV）上测试，验证其在多样城市场景中的野外表现。项目网站：https://lunarlab-gatech.github.io/ShelfGaussian/
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。