Search for: All records

In this paper, we study the 3D volumetric modeling problem by adopting the Wasserstein introspective neural networks method (WINN) that was previously applied to 2D static im ages. We name our algorithm 3DWINN which enjoys the same properties as WINN in the 2D case: being simultaneously generative and discriminative. Compared to the existing 3D volumetric modeling approaches, 3DWINN demonstrates competitive results on several benchmarks in both the generation and the classification tasks. In addition to the standard inception score, the Fréchet Inception Distance (FID) metric is also adopted to measure the quality of 3D volumetric generations. In addition, we study adversarial attacks for volumetric data and demonstrate the robustness of 3DWINN against ad- versarial examples while achieving appealing results in both classification and generation within a single model. 3DWINN is a general framework and it can be applied to the emerging tasks for 3D object and scene modeling 

Abstract Passive daytime radiative cooling (PDRC) can realize electricity‐free cooling by reflecting sunlight and emitting heat to the cold space. Current PDRC designs often involve costly vacuum processing or a large quantity of harmful organic solvents. Aqueous and paint‐like processing is cost‐effective and environmentally benign, thereby highly attractive for green manufacturing of PDRC coatings. However, common polymers explored in PDRC are difficult to disperse in water, let alone forming porous structures for efficient cooling. Here, a simple “bottom‐up” ball milling approach to create uniform microassembly of poly(vinylidene fluoride‐co‐hexafluoropropene) nanoparticles is reported. The micro‐ and nanopores among secondary particles and primary particles substantially enhance light scattering and results in excellent PDRC performance. A high solar reflectance of 0.94 and high emittance of 0.97 are achieved, making the coating 3.3 and 1.7 °C cooler than commercial white paints and the ambient temperature, under a high solar flux of ≈1100 W m⁻². More importantly, the volatile organic compound content in the aqueous paint is only 71 g L⁻¹. This satisfies the general regulatory requirements, which are critical to sustainability and practical applications.