arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1905.07503cs.CV
收藏

3DViewGraph:基于注意力的无序视图图的三维建模全局特征学习

3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention

Tsinghua University(清华大学);Beijing National Research Center for Information Science and Technology (BNRist)(北京信息科学与技术国家研究中心(BNRist));University of Maryland, College Park(马里兰大学帕克分校);University of Macau(澳门大学)

Zhizhong Han, Xiyang Wang, Chi-Man Vong, Yu-Shen Liu, Matthias Zwicker, C. L. Philip Chen

摘要:

通过在多个视图上聚合信息来学习全局特征已被证明对于3D形状分析是有效的。对于深度学习模型中的视图聚合,池化已被广泛应用。然而,池化导致视图内的内容和视图之间的空间关系的丢失,这限制了学习特征的可辨别性。我们提出了3DViewGraph来解决这个问题,它通过更有效地聚集无序视图来学习3D全局特征。具体地,围绕形状获取的无序视图被视为视图图上的视图节点。3DViewGraph首先学习一种新的潜在语义映射,将低层视图特征投影到由潜在语义模式跨越的低维空间中有意义的潜在语义嵌入中。然后,每对视图节点的内容和空间信息编码的一种新的空间模式的相关性,其中的相关性计算之间的潜在语义模式。最后,所有的空间模式的相关性与注意力权重学习一种新的注意力机制。这通过突出具有独特特征的无序视图节点并抑制具有外观模糊性的视图节点来进一步增加学习特征的可辨别性。我们证明了3DViewGraph在三个大规模基准测试中的表现优于最先进的方法。

英文摘要:

Learning global features by aggregating information over multiple views has been shown to be effective for 3D shape analysis. For view aggregation in deep learning models, pooling has been applied extensively. However, pooling leads to a loss of the content within views, and the spatial relationship among views, which limits the discriminability of learned features. We propose 3DViewGraph to resolve this issue, which learns 3D global features by more effectively aggregating unordered views with attention. Specifically, unordered views taken around a shape are regarded as view nodes on a view graph. 3DViewGraph first learns a novel latent semantic mapping to project low-level view features into meaningful latent semantic embeddings in a lower dimensional space, which is spanned by latent semantic patterns. Then, the content and spatial information of each pair of view nodes are encoded by a novel spatial pattern correlation, where the correlation is computed among latent semantic patterns. Finally, all spatial pattern correlations are integrated with attention weights learned by a novel attention mechanism. This further increases the discriminability of learned features by highlighting the unordered view nodes with distinctive characteristics and depressing the ones with appearance ambiguity. We show that 3DViewGraph outperforms state-of-the-art methods under three large-scale benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑