无需标注即可实现3D点云部件级推理，提升整体理解
PointCubeNet: 3D Part-level Reasoning with 3x3x3 Point Cloud Blocks
- 用3x3x3局部块结构分析点云子区域，结合文本标签进行细粒度理解
- 通过伪标签和局部损失函数实现无监督训练，性能媲美有监督方法
- 首次实现无标注的3D部件级推理，适合3D视觉与自动驾驶研究者
本文提出PointCubeNet，一种新型多模态3D理解框架，可在无需任何部件标注的情况下实现部件级推理。该框架包含全局分支与局部分支，其中局部分支由3x3x3局部块构成，可对点云子区域进行部件级分析，并关联对应的局部文本标签。通过提出的伪标签方法与局部损失函数，PointCubeNet可有效实现无监督训练。实验表明，对3D物体部件的理解显著提升了对整体3D物体的认知能力。这是首次尝试在无监督条件下实现3D部件级推理，并取得了可靠且有意义的结果。
原文摘要 · Abstract (English)
In this paper, we propose PointCubeNet, a novel multi-modal 3D understanding framework that achieves part-level reasoning without requiring any part annotations. PointCubeNet comprises global and local branches. The proposed local branch, structured into 3x3x3 local blocks, enables part-level analysis of point cloud sub-regions with the corresponding local text labels. Leveraging the proposed pseudo-labeling method and local loss function, PointCubeNet is effectively trained in an unsupervised manner. The experimental results demonstrate that understanding 3D object parts enhances the understanding of the overall 3D object. In addition, this is the first attempt to perform unsupervised 3D part-level reasoning and achieves reliable and meaningful results.
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。