Learning implicit templates as neural fields has recently shown impressive performance in unsupervised shape correspondence. Despite the success, we observe current approaches, which solely rely on geometric information, often learn suboptimal deformation across generic object shapes, which have high structural variability. In this paper, we highlight the importance of part deformation consistency and propose a semantic-aware implicit template learning framework to enable semantically plausible deformation. By leveraging semantic prior from a self-supervised feature extractor, we suggest local conditioning with novel semantic-aware deformation code and deformation consistency regularizations regarding part deformation, global deformation, and global scaling. Our extensive experiments demonstrate the superiority of the proposed method over baselines in various tasks: keypoint transfer, part label transfer, and texture transfer. More interestingly, our framework shows a larger performance gain under more challenging settings. We also provide qualitative analyses to validate the effectiveness of semantic-aware deformation. The code is available at https://github.com/mlvlab/PDC.

翻译：通过神经场学习隐式模板在无监督形状对应中展现了出色的性能。尽管取得了成功，我们观察到当前仅依赖几何信息的方法在处理具有高度结构变异性的通用物体形状时，往往学习到次优的变形。本文强调了部件变形一致性的重要性，并提出了一种语义感知的隐式模板学习框架，以实现语义上合理的变形。通过利用自监督特征提取器提供的语义先验，我们提出了局部条件化方法，结合新颖的语义感知变形编码以及关于部件变形、全局变形和全局缩放的变形一致性正则化。大量实验表明，所提方法在关键点迁移、部件标签迁移和纹理迁移等多种任务中优于基线方法。更有趣的是，我们的框架在更具挑战性的设置下表现出更大的性能提升。我们还通过定性分析验证了语义感知变形的有效性。代码已开源于 https://github.com/mlvlab/PDC。