We present imGHUM, the first holistic generative model of 3D human shape and articulated pose, represented as a signed distance function. In contrast to prior work, we model the full human body implicitly as a function zero-level-set and without the
use of an explicit template mesh. We propose a novel network architecture and a learning paradigm, which make it possible to learn a detailed implicit generative model of human pose, shape, and semantics, on par with state-of-the-art mesh-based models. Our model features desired detail for human models, such as articulated pose including hand motion and facial expressions, a broad spectrum of shape variations, and can be queried at arbitrary resolutions and spatial locations. Additionally, our model has attached spatial semantics making it straightforward to establish correspondences between different shape instances, thus enabling applications that are difficult to tackle using classical implicit representations. In extensive experiments, we demonstrate the model accuracy and its applicability to current research problems.
3D ED is an effective technique to determine the structures of submicron- or nano-sized crystals. In this paper, we implemented energy-filtered 3D ED using a Gatan Energy Filter (GIF) in both selected area electron diffraction mode and micro/nanoprob
e mode. We explained the setup in detail, which improves the accessibility of energy-filtered 3D ED experiments as more electron microscopes are equipped with a GIF than an in-column filter. We also proposed a crystal tracking method in STEM mode using live HAADF image stream. This method enables us to collect energy-filtered 3D ED datasets in STEM mode with a larger tilt range without foregoing any frames. In order to compare the differences between energy-filtered 3D ED and normal 3D ED data, three crystalline samples have been studied in detail. We observed that the final R1 will improve 20% to 30% for energy-filtered datasets compared with unfiltered datasets and the structure became more reasonable. We also discussed the possible reasons that lead to the improvement.
3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to the sparse
ness of the point cloud and the complexity of urban scenes. Semi-supervised learning is a promising technique to mitigate the data annotation issue. Inspired by this, we propose a novel semi-supervised framework based on pseudo-labeling for outdoor 3D object detection tasks. We design the Adaptive Class Confidence Selection module (ACCS) to generate high-quality pseudo-labels. Besides, we propose Holistic Point Cloud Augmentation (HPCA) for unlabeled data to improve robustness. Experiments on the KITTI benchmark demonstrate the effectiveness of our method.
Monocular 3D human pose and shape estimation is challenging due to the many degrees of freedom of the human body and thedifficulty to acquire training data for large-scale supervised learning in complex visual scenes. In this paper we present practic
al semi-supervised and self-supervised models that support training and good generalization in real-world images and video. Our formulation is based on kinematic latent normalizing flow representations and dynamics, as well as differentiable, semantic body part alignment loss functions that support self-supervised learning. In extensive experiments using 3D motion capture datasets like CMU, Human3.6M, 3DPW, or AMASS, as well as image repositories like COCO, we show that the proposed methods outperform the state of the art, supporting the practical construction of an accurate family of models based on large-scale training with diverse and incompletely labeled image and video data.
The model of ideal fluid flow around a cylindrical obstacle exhibits a long-established physical picture where originally straight streamlines will be deflected over the whole space by the obstacle. As inspired by transformation optics and metamateri
als, recent theories have proposed the concept of fluid cloaking able to recover the straight streamlines as if the obstacle does not exist. However, such a cloak, similar to all previous transformation-optics-based devices, relies on complex metamaterials, being difficult to implement. Here we deploy the theory of scattering cancellation and report on the experimental realization of a fluid-flow cloak without metamaterials. This cloak is realized by engineering the geometry of the fluid channel, which effectively cancels the dipole-like scattering of the obstacle. The cloaking effect is demonstrated via direct observation of the recovered straight streamlines in the fluid flow with injected dyes. Our work sheds new light on conventional fluid control and may find applications in microfluidic devices.
