通过风格调制生成对抗网络实现多样化形状补全
Diverse Shape Completion via Style Modulated Generative Adversarial Networks
AI总结：
提出一种基于风格调制生成对抗网络的条件生成模型，通过引入随机性、风格码分布学习及多尺度多样性惩罚，在无需多真实值的情况下实现部分点云的多样化合理补全。
摘要：
形状补全旨在从部分观测中恢复物体的完整3D几何形状。这个问题本质上是多模态的，因为有许多方法可以合理地补全形状的缺失区域。这种多样性能够反映形状潜在的不确定性，并且对于规划等下游任务可能更为可取。在本文中，我们提出了一种新颖的条件生成对抗网络，能够为部分观测到的点云生成许多多样化且合理的补全结果。为了使我们的网络能够对相同的部分输入产生多种补全结果，我们通过风格调制将随机性引入网络。通过在训练期间从完整形状中提取风格码，并学习它们的分布，我们的风格码可以显式地携带形状类别信息，从而带来更好的补全效果。我们进一步引入了多尺度的多样性惩罚和判别器，以防止条件模式崩溃，并且在训练时无需为每个部分输入提供多个真实补全结果。在多个合成和真实数据集上的评估表明，我们的方法在尊重部分观测的同时获得了更大的补全多样性，取得了显著的改进。
英文摘要：
Shape completion aims to recover the full 3D geometry of an object from a partial observation. This problem is inherently multi-modal since there can be many ways to plausibly complete the missing regions of a shape. Such diversity would be indicative of the underlying uncertainty of the shape and could be preferable for downstream tasks such as planning. In this paper, we propose a novel conditional generative adversarial network that can produce many diverse plausible completions of a partially observed point cloud. To enable our network to produce multiple completions for the same partial input, we introduce stochasticity into our network via style modulation. By extracting style codes from complete shapes during training, and learning a distribution over them, our style codes can explicitly carry shape category information leading to better completions. We further introduce diversity penalties and discriminators at multiple scales to prevent conditional mode collapse and to train without the need for multiple ground truth completions for each partial input. Evaluations across several synthetic and real datasets demonstrate that our method achieves significant improvements in respecting the partial observations while obtaining greater diversity in completions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
