arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.13244cs.CVcs.LG
收藏

MVTN:用于三维形状识别的多视图变换网络

MVTN: Multi-View Transformation Network for 3D Shape Recognition

King Abdullah University of Science and Technology (KAUST)(阿卜杜拉国王科技大学)

Abdullah Hamdi, Silvio Giancola, Bernard Ghanem

摘要:

多视图投影方法已经证明了它们在3D形状识别上达到最先进性能的能力。这些方法学习从多个视图中聚合信息的不同方法。然而,对于所有形状,这些视图的摄像机视点往往是逐行设置和固定的。为了避免目前的多视图方法缺乏动态性,我们建议学习这些观点。特别是,我们介绍了多视图转换网络(MVTN),回归最佳视点的3D形状识别,建立在可微渲染的进步。因此,MVTN可以与任何多视图网络一起进行端到端训练,以进行3D形状分类。我们将MVTN集成到一个新的自适应多视图管道中,该管道可以渲染3D网格或点云。MVTN在3D形状分类和3D形状检索任务中表现出明显的性能增益,而无需额外的训练监督。在这些任务中,MVTN在ModelNet40、ShapeNet Core55和最新的真实ScanObjectNN数据集上实现了最先进的性能(最多提高6%)。有趣的是,我们还证明了MVTN可以在3D域中提供对旋转和遮挡的网络鲁棒性。该代码可在https://github.com/ajhamdi/MVTN上获得。

英文摘要:

Multi-view projection methods have demonstrated their ability to reach state-of-the-art performance on 3D shape recognition. Those methods learn different ways to aggregate information from multiple views. However, the camera view-points for those views tend to be heuristically set and fixed for all shapes. To circumvent the lack of dynamism of current multi-view methods, we propose to learn those view-points. In particular, we introduce the Multi-View Transformation Network (MVTN) that regresses optimal view-points for 3D shape recognition, building upon advances in differentiable rendering. As a result, MVTN can be trained end-to-end along with any multi-view network for 3D shape classification. We integrate MVTN in a novel adaptive multi-view pipeline that can render either 3D meshes or point clouds. MVTN exhibits clear performance gains in the tasks of 3D shape classification and 3D shape retrieval without the need for extra training supervision. In these tasks, MVTN achieves state-of-the-art performance on ModelNet40, ShapeNet Core55, and the most recent and realistic ScanObjectNN dataset (up to 6% improvement). Interestingly, we also show that MVTN can provide network robustness against rotation and occlusion in the 3D domain. The code is available at https://github.com/ajhamdi/MVTN .

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。

↑