论文标题
PATCHOMPLETE：在看不见的类别上学习3D形状完成的多分辨率补丁检验
PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories
论文作者
论文摘要
尽管3D形状表示能够在许多视觉和感知应用中实现强大的推理，但学习3D形状先验倾向于将培训的特定类别限制在培训的特定类别中，导致学习过程效率低下，尤其是对于具有看不见类别的一般应用。因此，我们提出了补丁程序，该贴片是根据多分辨率的本地贴片学习有效的形状先验，通常比完整形状（例如，椅子和桌子经常共享腿）更通用，因此可以对看不见的类别类别进行几何推理。为了学习这些共享的子结构，我们学习了所有火车类别的多分辨率补丁验证者，然后通过整个贴片研究人员的注意与输入部分形状观察相关联，并最终将其解码为完整的形状重建。此类基于补丁的先验避免过度适合特定的火车类别，并在测试时间对完全看不见的类别进行重建。我们证明了方法对合成造型的数据的有效性以及扫描仪中的实际扫描对象，包括噪声和混乱，在新型类别形状的完整状态下改善了塑形距离的最新情况，在碎屑上的距离为19.3％，扫描仪的9.0％。
While 3D shape representations enable powerful reasoning in many visual and perception applications, learning 3D shape priors tends to be constrained to the specific categories trained on, leading to an inefficient learning process, particularly for general applications with unseen categories. Thus, we propose PatchComplete, which learns effective shape priors based on multi-resolution local patches, which are often more general than full shapes (e.g., chairs and tables often both share legs) and thus enable geometric reasoning about unseen class categories. To learn these shared substructures, we learn multi-resolution patch priors across all train categories, which are then associated to input partial shape observations by attention across the patch priors, and finally decoded into a complete shape reconstruction. Such patch-based priors avoid overfitting to specific train categories and enable reconstruction on entirely unseen categories at test time. We demonstrate the effectiveness of our approach on synthetic ShapeNet data as well as challenging real-scanned objects from ScanNet, which include noise and clutter, improving over state of the art in novel-category shape completion by 19.3% in chamfer distance on ShapeNet, and 9.0% for ScanNet.
