Single-view 3D object reconstruction has seen much progress, yet methods still struggle generalizing to novel shapes unseen during training. Common approaches predominantly rely on learned global shape priors and, hence, disregard detailed local observations. In this work, we address this issue by learning a hierarchy of priors at different levels of locality from ground truth input depth maps. We argue that exploiting local priors allows our method to efficiently use input observations, thus improving generalization in visible areas of novel shapes. At the same time, the combination of local and global priors enables meaningful hallucination of unobserved parts resulting in consistent 3D shapes. We show that the hierarchical approach generalizes much better than the global approach. It generalizes not only between different instances of a class but also across classes and to unseen arrangements of objects.
翻译:单一视图 3D 对象重建已经取得了很大进展, 但方法仍然难以推广到培训期间看不见的新形状。 共同方法主要依靠学习的全球形状前科,因此忽略了详细的当地观察。 在这项工作中,我们通过从地面真相输入深度地图中学习不同级别地点的前科等级来解决这个问题。 我们争辩说,利用当地前科使我们能够有效地使用输入观测,从而改进新形状可见地区的一般化。 同时,地方和全球前科相结合,能够对未观察到的部分产生有意义的幻觉,从而形成一致的3D 形状。 我们表明,分级方法比全球方法要简单得多。 它不仅概括了班级的不同情况,而且概括了班级的不同情况,还概括了物体的无形安排。