GeoFree-CoSeg：无需几何对齐的无监督点云-图像跨模态共分割
GeoFree-CoSeg: Unsupervised Point Cloud-Image Cross-Modal Co-Segmentation Without Geometric Alignment
提出无需几何对齐的点云-图像跨模态共分割设定，用跨模态公共语义图把2D/3D粗语义提纯为细粒度公共语义并互相增强，为多模态无监督分割提供了可复用的特征提纯与互增强框架。
原文依据 a cross-modal common semantic graph purifies these features into fine-grained common semantics
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论共分割旨在从一组点云或图像中识别并分割出公共对象。现有方法聚焦于单模态共分割。然而，单模态有限的语义信息制约了公共对象的发现，并导致分割掩码的标注成本高昂且耗费人力。相比之下，跨模态共分割同时利用两种模态，具有两个关键优势：(i) 额外的语义线索可弥补分割掩码的缺失；(ii) 互补的模态提供了超越单模态方法局限的更丰富的公共语义。受这些挑战的驱动，我们引入一项新任务：无监督点云-图像跨模态共分割。我们采用由粗到细的策略解决该问题。首先，3D 与 2D 分支分别从各自模态中提取粗粒度的公共语义。随后，跨模态公共语义图将这些特征提纯为细粒度的公共语义。最后，3D 与 2D 公共语义特征相互增强，且无需几何对齐。在两个标准点云基准和两个对应的图像共分割数据集上的实验表明，我们的方法优于现有无监督最优方法。
英文原文摘要 1282 字符
Co-segmentation aims to identify and segment common objects across a set of point clouds or images. Existing methods focus on single-modal co-segmentation. However, the limited semantics of a single modality restrict the discovery of common objects, leading to costly and labor-intensive segmentation masks. In contrast, cross-modal co-segmentation leverages both modalities, offering two key advantages: (i) additional semantic cues compensate for the absence of segmentation masks; and (ii) complementary modalities provide richer common semantics beyond the limitations of single-modality approaches. Motivated by these challenges, we introduce a novel task: unsupervised point cloud-image cross-modal co-segmentation. We tackle this problem using a coarse-to-fine approach. First, the 3D and 2D branches extract coarse common semantics from each modality, respectively. Then, a cross-modal common semantic graph purifies these features into fine-grained common semantics. Finally, 3D and 2D common semantic features are mutually enhanced, without requiring geometric alignment. Experiments on two standard point cloud benchmarks and two corresponding image co-segmentation datasets demonstrate our superior performance compared to existing unsupervised state-of-the-art methods.