Fig. 1. Renderings of objects captured and modeled by our system. The input to our method consists of synchronized and calibrated multi-view video. We build a dynamic, volumetric representation of the scene by training an encoder-decoder network end-to-end using a differentiable ray marching algorithm.Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain complex phenomena such as thin structures, evolving topology, translucency, scattering, occlusion, and biological motion. Mesh-based reconstruction and tracking often fail in these cases, and other approaches (e.g., light field video) typically rely on constrained viewing conditions, which limit interactivity. We circumvent these difficulties by presenting a learningbased approach to representing dynamic objects inspired by the integral projection model used in tomographic imaging. The approach is supervised directly from 2D images in a multi-view capture setting and does not require explicit reconstruction or tracking of the object. Our method has two primary components: an encoder-decoder network that transforms input images into a 3D volume representation, and a differentiable ray-marching operation that enables end-to-end training. By virtue of its 3D representation, our construction extrapolates better to novel viewpoints compared to screen-space rendering techniques. The encoder-decoder architecture learns a latent representation of a dynamic scene that enables us to produce novel content sequences not seen during training. To overcome memory limitations of voxel-based representations, we learn a dynamic irregular grid structure implemented with a warp field during ray-marching. This structure greatly improves the apparent resolution and reduces grid-like artifacts and jagged motion. Finally, we demonstrate how to incorporate surface-based representations into our volumetric-learning framework for applications

Background & methods Recent social movements have highlighted fatal police violence as an enduring public health problem in the United States. To solve it, the public requires basic information, such as understanding where rates of fatal police violence are particularly high, and for which groups. Existing mapping efforts, though critically important, often use inappropriate statistical methods and can produce misleading, unstable rates when denominators are small. To fill this gap, we use inverse-variance-weighted multilevel models to estimate overall and race-stratified rates of fatal police violence for all Metropolitan Statistical Areas (MSAs) in the U.S. (2013-2017), as well as racial inequities in these rates. We analyzed the most recent, reliable data from Fatal Encounters, a citizen science initiative that aggregates and verifies media reports. Results Rates of police-related fatalities varied dramatically, with the deadliest MSAs exhibiting rates nine times those of the least deadly. Overall rates in Southwestern MSAs were highest, with lower rates in the northern Midwest and Northeast. Yet this pattern was reversed for Black-White inequities, with Northeast and Midwest MSAs exhibiting the highest inequities nationwide. Our main results excluded deaths that could be considered accidents (e.g., vehicular collisions), but sensitivity analyses demonstrated that doing so may underestimate the rate of fatal police violence in some MSAs by 60%. Black-White and Latinx-White inequities were slightly underestimated nationally by excluding reportedly 'accidental' deaths, but MSA-specific inequities were sometimes severely under-or overestimated. Conclusions Preventing fatal police violence in different areas of the country will likely require unique solutions. Estimates of the severity of these problems (overall rates, racial inequities, specific causes of death) in any given MSA are quite sensitive to which types of deaths are analyzed, and whether race and cause of death are attributed correctly. Monitoring and

No abstract

Humans implicitly rely on properties of the materials that make up ordinary objects to guide our interactions. Grasping smooth materials, for example, requires more care than rough ones, and softness is an ideal property for fabric used in bedding. Even when these properties are not purely visual (softness is a physical property of the material), we may still infer the softness of a fabric by looking at it. We refer to these visually-recognizable material properties as visual material attributes. Recognizing visual material attributes in images can contribute valuable information for general scene understanding and for recognition of materials themselves. Unlike wellknown object and scene attributes, visual material attributes are local properties. "Fuzziness", for example, does not have a particular shape. We show that given a set of images annotated with known material attributes, we may accurately recognize the attributes from purely local information (small image patches). Obtaining such annotations in a consistent fashion at scale, however, is challenging. We introduce a method that allows us to solve this problem by probing the human visual perception of materials to automatically discover unnamed attributes that serve the same purpose. By asking simple yes/no questions comparing pairs of image patches, we obtain sufficient weak supervision to build a set of attributes (and associated classifiers) that, while being unnamed, serve the same function as the named attributes, such as "fuzzy" or "rough", with which we describe materials. Doing so allows us to recognize visual material attributes without resorting to exhaustive manual annotation of a fixed set of named attributes. Furthermore, we show that our automatic attribute discovery method may be integrated in the end-to-end learning of a material classification CNN framework to simultaneously recognize materials and discover their visual material attributes. Our experimental results show that visual material attributes, whether named or automatically discovered, provide a useful intermediate representation for known material categories themselves as well as a basis for transfer learning when recognizing previously-unseen categories.Index Terms-visual material attributes, human material perception, material recognition ! The authors are with the

No abstract