The key challenge in single image 3D shape reconstruction is to ensure that deep models can generalize to shapes which were not part of the training set. This is challenging because the algorithm must infer the occluded portion of the surface by leveraging a representation learned based on the shape characteristics of the training data, and is therefore vulnerable to overfitting. Such generalization to unseen categories of objects is a function of both architecture design and training approaches. This paper introduces SDFNet, a novel shape prediction architecture and training approach which supports effective generalization. We provide an extensive investigation of the factors which influence generalization accuracy and its measurement, ranging from the consistent use of 3D shape metrics to the choice of rendering approach and the large-scale evaluation on unseen shapes using ShapeNetCore.v2 and ABC. We show that SDFNet provides state-of-the-art performance on seen and unseen shapes relative to existing baseline methods GenRe and OccNet. We provide the first large-scale experimental evaluation of generalization performance. The codebase released with this article will allow for the consistent evaluation and comparison of methods for single image shape reconstruction.
翻译:单一图像 3D 形状重建的关键挑战是确保深层模型能够概括到不是培训集的一部分的形状,这是具有挑战性的,因为算法必须利用根据培训数据的形状特征所学的表示法,推断表面的隐蔽部分,因此容易过度适应。这种对不可见物体类别的概括性是建筑设计和培训方法的功能。本文介绍了SDFNet,一种支持有效概括化的新型形状预测结构和培训方法。我们广泛调查了影响一般化精确度及其测量的因素,从持续使用3D 形状的衡量标准到使用 ShapeNetCore.v2 和 ABC 选择投影法和对不可见形状进行大规模评价。我们表明,SDFNet 提供了与现有基线方法GenRe 和 OccNet 相比的可见和不可见的形状状态表现。我们提供了对一般化性能的第一次大规模实验性评估。我们所释放的代码库将允许对单一图像形状重建方法进行一致的评价和比较。