We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV position map which records the 3D shape of a complete face in UV space, then train a simple Convolutional Neural Network to regress it from a single 2D image. We also integrate a weight mask into the loss function during training to improve the performance of the network. Our method does not rely on any prior face model, and can reconstruct full facial geometry along with semantic meaning. Meanwhile, our network is very light-weighted and spends only 9.8ms to process an image, which is extremely faster than previous works. Experiments on multiple challenging datasets show that our method surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin. Code is available at https://github.com/YadiraF/PRNet.
In eastern China Palaeozoic kimberlites and Cenozoic basalts have been erupted through the same Archaean crust, thus providing deep probes of the cratonic lower lithosphere over a period of 400 Ma. While Palaeozoic diamondiferous kimberlites point to the existence of thick, refractory lower lithosphere in the east, Cenozoic basalt-borne xenoliths reveal the presence of hot, thin, less refractory lower lithosphere. Remnants of the Archaean lithosphere may have survived as harzburgites which are chemically similar to those from the Kaapvaal craton but very different from recently accreted lherzolites. In the absence of convincing evidence for supra-subduction or intraplate processes it is believed that the dramatic change of lithosphere architecture in the Phanerozoic was caused by indentor tectonics resulting from the collision of India and Eurasia. Passive reactivation and remobilization of the Archaean lower lithosphere, in particular metasome horizons, contributed to Cenozoic magmatism aligned along major lithospheric faults.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.