Figure 1: We present Pix3D, a new large-scale dataset of diverse image-shape pairs. Each 3D shape in Pix3D is associated with a rich and diverse set of images, each with an accurate 3D pose annotation to ensure precise 2D-3D alignment. In comparison, existing datasets have limitations: 3D models may not match the objects in images; pose annotations may be imprecise; or the dataset may be relatively small. AbstractWe study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related tasks including reconstruction, retrieval, viewpoint estimation, etc. Building such a large-scale dataset, however, is highly challenging; existing datasets either contain only synthetic data, or lack precise alignment between 2D images and 3D shapes, or only have a small number of images. Second, we calibrate the evaluation criteria for 3D shape reconstruction through behavioral studies, and use them to objectively and systematically benchmark cuttingedge reconstruction algorithms on Pix3D. Third, we design a novel model that simultaneously performs 3D reconstruction and pose estimation; our multi-task learning approach achieves state-of-the-art performance on both tasks. * Only 90 of the 219 shapes in the IKEA dataset have associated images. † https://structure.io ‡ https://occipital.com

MSCs treatment can protect against experimental liver fibrosis in CCl4-induced or DMN-induced rats and the mechanisms of the anti-fibrosis by MSCs will be studied further.

The problem of single-view 3D shape completion or reconstruction is challenging, because among the many possible shapes that explain an observation, most are implausible and do not correspond to natural objects. Recent research in the field has tackled this problem by exploiting the expressiveness of deep convolutional networks. In fact, there is another level of ambiguity that is often overlooked: among plausible shapes, there are still multiple shapes that fit the 2D image equally well; i.e., the ground truth shape is non-deterministic given a single-view input. Existing fully supervised approaches fail to address this issue, and often produce blurry mean shapes with smooth surfaces but no fine details. In this paper, we propose ShapeHD, pushing the limit of single-view shape completion and reconstruction by integrating deep generative models with adversarially learned shape priors. The learned priors serve as a regularizer, penalizing the model only if its output is unrealistic, not if it deviates from the ground truth. Our design thus overcomes both levels of ambiguity aforementioned. Experiments demonstrate that ShapeHD outperforms state of the art by a large margin in both shape completion and shape reconstruction on multiple real datasets.

Little things matter Particulate air pollution 2.5 micrometers or smaller in size (PM2.5) is a major cause of human mortality, and controlling its production is a health policy priority. Nitrogen oxides are an important precursor of PM2.5 and have been a focus of pollution control programs. However, Gu et al . now show that abating ammonia emissions is also an important component of PM2.5 reduction, and the societal benefits of abatement greatly outweigh the costs (see the Perspective by Erisman). Reducing ammonia emissions thus would be a cost-effective complement to nitrogen oxides and sulfur dioxide controls. —HJS