论文标题
来自模棱两可的深度图像的多样化形状完成
Diverse Plausible Shape Completions from Ambiguous Depth Images
论文作者
论文摘要
我们提出了PSSNET，这是一种网络体系结构，用于从单个2.5D深度图像中生成各种合理的3D重建。即使多种形状与观察结果一致，现有方法倾向于在单个形状上产生较小的变化。 To obtain diversity we alter a Variational Auto Encoder by providing a learned shape bounding box feature as side information during training.由于这些功能在训练过程中已知，因此我们能够为编码器增加监督损失，并为解码器添加无声的值。为了评估，我们从网络中采样了一组完成，为每个测试观察构建一组合理的形状匹配，并使用我们在形状集上的合理多样性度量进行比较。我们使用Shapenet杯子和部分封闭的YCB对象执行实验，发现我们的方法在数据集中的性能很少，而当许多形状合适地符合观察到的深度图像时，我们的方法的表现就胜过现有的方法。我们在遮挡和混乱中抓住物体时在物理机器人上证明了一种用于PSSNET的用途。
We propose PSSNet, a network architecture for generating diverse plausible 3D reconstructions from a single 2.5D depth image. Existing methods tend to produce only small variations on a single shape, even when multiple shapes are consistent with an observation. To obtain diversity we alter a Variational Auto Encoder by providing a learned shape bounding box feature as side information during training. Since these features are known during training, we are able to add a supervised loss to the encoder and noiseless values to the decoder. To evaluate, we sample a set of completions from a network, construct a set of plausible shape matches for each test observation, and compare using our plausible diversity metric defined over sets of shapes. We perform experiments using Shapenet mugs and partially-occluded YCB objects and find that our method performs comparably in datasets with little ambiguity, and outperforms existing methods when many shapes plausibly fit an observed depth image. We demonstrate one use for PSSNet on a physical robot when grasping objects in occlusion and clutter.
