在本文中，我们介绍了一条神经渲染管道，用于将一个人在源视频中的面部表情，头部姿势和身体运动转移到目标视频中的另一个人。我们将方法应用于手语视频的具有挑战性的案例：给定手语用户的源视频，我们可以忠实地传输执行的手册（例如握手，棕榈方向，运动，位置）和非手术（例如，眼睛凝视，凝视，面部表情，头部移动）以照片真实的方式标志着目标视频。为了有效捕获上述提示，这些线索对于手语交流至关重要，我们以最近引入的最健壮和最可靠的深度学习方法的有效组合来建立。使用3D感知表示，将身体部位的估计运动组合并重新定位到目标签名者。然后将它们作为我们的视频渲染网络的条件输入，从而生成时间一致和照片现实的视频。我们进行了详细的定性和定量评估和比较，这些评估和比较证明了我们的方法的有效性及其对现有方法的优势。我们的方法产生了前所未有的现实主义的有希望的结果，可用于手语匿名。此外，它很容易适用于重新制定其他类型的全身活动（舞蹈，表演，锻炼等）以及手语生产系统的合成模块。
translated by 谷歌翻译
Real-world robotic grasping can be done robustly if a complete 3D Point Cloud Data (PCD) of an object is available. However, in practice, PCDs are often incomplete when objects are viewed from few and sparse viewpoints before the grasping action, leading to the generation of wrong or inaccurate grasp poses. We propose a novel grasping strategy, named 3DSGrasp, that predicts the missing geometry from the partial PCD to produce reliable grasp poses. Our proposed PCD completion network is a Transformer-based encoder-decoder network with an Offset-Attention layer. Our network is inherently invariant to the object pose and point's permutation, which generates PCDs that are geometrically consistent and completed properly. Experiments on a wide range of partial PCD show that 3DSGrasp outperforms the best state-of-the-art method on PCD completion tasks and largely improves the grasping success rate in real-world scenarios. The code and dataset will be made available upon acceptance.
translated by 谷歌翻译