论文标题
飞机与椅子：类别引导3D形状学习，没有任何3D提示
Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues
论文作者
论文摘要
我们提出了一种新颖的3D形状重建方法，该方法学会了从单个RGB图像预测隐式3D形状表示。我们的方法使用一组无需观点注释的多个对象类别的单视图像，迫使模型在没有3D监督的情况下跨多个对象类别学习。为了通过如此最小的监督来促进学习，我们使用类别标签通过一种新颖的分类度量学习方法来指导学习。我们还利用对抗和观点正则化技术进一步解散了观点和形状的影响。我们使用没有任何3D提示的单个模型获得了大规模（超过50个类别）单视点形状预测的第一个结果。我们也是第一个检查和量化单视图3D形状重建中类信息的好处的人。我们的方法比Shapenet-13，Shapenet-55和Pascal3d+的最先进方法实现了优越的性能。
We present a novel 3D shape reconstruction method which learns to predict an implicit 3D shape representation from a single RGB image. Our approach uses a set of single-view images of multiple object categories without viewpoint annotation, forcing the model to learn across multiple object categories without 3D supervision. To facilitate learning with such minimal supervision, we use category labels to guide shape learning with a novel categorical metric learning approach. We also utilize adversarial and viewpoint regularization techniques to further disentangle the effects of viewpoint and shape. We obtain the first results for large-scale (more than 50 categories) single-viewpoint shape prediction using a single model without any 3D cues. We are also the first to examine and quantify the benefit of class information in single-view supervised 3D shape reconstruction. Our method achieves superior performance over state-of-the-art methods on ShapeNet-13, ShapeNet-55 and Pascal3D+.
