论文标题
通过对抗形状先验的隐性形状完成
Implicit Shape Completion via Adversarial Shape Priors
论文作者
论文摘要
我们为部分点云完成了一种新型的神经隐式形状方法。为此，我们将有条件的深-SDF体系结构与学习的，对抗性的先验相结合。更具体地说，我们的网络将部分输入转换为全局潜在代码，然后通过隐式的，签名的距离生成器恢复完整的几何形状。此外，我们训练一个点网++判别器，该歧视器促使发电机产生合理的，全球一致的重建。这样，我们有效地将预测既现实的形状的挑战，即模仿训练集的姿势分布，并在复制部分输入观察结果的意义上进行准确。在我们的实验中，我们展示了完成部分形状的最新性能，考虑到人造物体（例如飞机，椅子，...）和可变形的形状类别（人体）。最后，我们表明我们的对抗训练方法会导致视觉上合理的重建，这些重建在恢复给定对象的缺失部分方面非常一致。
We present a novel neural implicit shape method for partial point cloud completion. To that end, we combine a conditional Deep-SDF architecture with learned, adversarial shape priors. More specifically, our network converts partial inputs into a global latent code and then recovers the full geometry via an implicit, signed distance generator. Additionally, we train a PointNet++ discriminator that impels the generator to produce plausible, globally consistent reconstructions. In that way, we effectively decouple the challenges of predicting shapes that are both realistic, i.e. imitate the training set's pose distribution, and accurate in the sense that they replicate the partial input observations. In our experiments, we demonstrate state-of-the-art performance for completing partial shapes, considering both man-made objects (e.g. airplanes, chairs, ...) and deformable shape categories (human bodies). Finally, we show that our adversarial training approach leads to visually plausible reconstructions that are highly consistent in recovering missing parts of a given object.
