- 3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians
To overcome these limitations, we present 3DAffordSplat, the first large-scale, multi-modal dataset tailored for 3DGS-based affordance reasoning This dataset includes 23,677 Gaussian instances, 8,354 point cloud instances, and 6,631 manually annotated affordance labels, encompassing 21 object categories and 18 affordance types
- 3DAffordSplat - hcplab-sysu. github. io
To overcome these limitations, we present 3DAffordSplat, the first large-scale, multi-modal dataset tailored for 3DGS-based affordance reasoning This dataset includes 23k Gaussian instances, 8 3k point cloud instances, and 6 6k manually annotated affordance labels, encompassing 21 object categories and 18 affordance types
- 3DAffordSplat|3D高斯泼溅数据集|功能推理数据集
3DAffordSplat是首个针对3D高斯泼溅（3DGS）的 affordance 推理任务构建的大规模多模态数据集，包含23,677个高斯实例、8,354个点云实例和6,631个人工标注的affordance标签，涵盖21个物体类别和18种affordance类型。
- Weizm AffordSplat · Datasets at Hugging Face
In this repository, we present 3DAffordSplat, the first large-scale, multi-modal dataset tailored for 3DGS-based affordance reasoning This dataset includes 23k Gaussian instances, 8k point cloud instances, and 6k manually annotated affordance labels, encompassing 21 object categories and 18 affordance types
- 创新跨模态结构对齐模块！3DAffordSplat：首个专为3DGS设计的大规模多模态功能数据集-CSDN博客
3DAffordSplat是首个专为3DGS设计的大规模多模态功能数据集，通过丰富的物体类别和功能类型标注填补了该领域空白。 基于此构建的AffordSplatNet模型创新性地采用跨模态结构对齐模块，有效弥合了点云与高斯表示之间的鸿沟，实现了更精准鲁棒的功能推理。
- 3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians
We introduce 3DAffordSplat, the first large-scale, multi-modal 3DGS-based Affordance Reasoning with comprehensive affordance annotations, comprising Gaussian, point cloud, and textual instruction modalities
- [论文审查] 3DAffordSplat: Efficient Affordance Reasoning with 3D Gaussians
该论文介绍了一种名为 3DAffordSplat 的新型大规模多模态数据集，专为基于 3D Gaussian Splatting (3DGS) 的可供性推理而设计。 论文同时提出了一种名为 AffordSplatNet 的新颖模型，该模型利用 3DGS 表示进行可供性推理。
- 多模态大模型的跨模态对齐模块有哪些工作？ - 知乎
3DAffordSplat是首个专为3DGS设计的大规模多模态功能数据集，通过丰富的物体类别和功能类型标注填补了该领域空白。 基于此构建的AffordSplatNet模型创新性地采用跨模态结构对齐模块，有效弥合了点云与高斯表示之间的鸿沟，实现了更精准鲁棒的功能推理。
|