AnyFace++: A Unified Framework for Free-style Text-to-Face Synthesis and Manipulation.

Human faces contain rich semantic information that could hardly be described without a large vocabulary and complex sentence patterns. However, most existing text-to-image synthesis methods could only generate meaningful results based on limited sentence templates with words contained in the training set, which heavily impairs the generalization ability of these models. In this paper, we define a novel 'free-style' text-to-face generation and manipulation problem, and propose an effective solution, named AnyFace++, which is applicable to a much wider range of open-world scenarios. The CLIP model is involved in AnyFace++ for learning an aligned language-vision feature space, which also expands the range of acceptable vocabulary as it is trained on a large-scale dataset. To further improve the granularity of semantic alignment between text and images, a memory module is incorporated to convert the description with arbitrary length, format, and modality into regularized latent embeddings representing discriminative attributes of the target face. Moreover, the diversity and semantic consistency of generation results are improved by a novel semi-supervised training scheme and a series of newly proposed objective functions. Compared to state-of-the-art methods, AnyFace++ is capable of synthesizing and manipulating face images based on more flexible descriptions and producing realistic images with higher diversity.

Effect of scanning speeds on mechanical properties of CoCrNi medium entropy alloy prepared by laser additive manufacturing.

Medium entropy alloy (MEA) is a hot spot in the field of material research in recent years. At present, the most widely used processing method of MEAs is "casting-rolling-heat treatment", and the preparation of CoCrNi MEA by laser additive manufacturing (LAM) is still in primary stage. In this study, CoCrNi MEAs were fabricated with different scanning speeds by laser additive manufacturing, and the influence of scanning speed on its mechanical properties was investigated. The results show that higher scanning speed can significantly improve the mechanical properties of CoCrNi MEA. Compared with the low-speed laser additive manufacturing (LSLAM) MEA, the tensile strength of high-speed laser additive manufacturing (HSLAM) MEA is increased by 5.6 % and the fracture strain is increased by 60 %, which is mainly due to the entanglement of 1/6<112> and 1/2<110> dislocations and the defect structure at the grain boundary. LAM is a promising technology that can promote the development and application of MEAs in industry.

GAN-Based Facial Attribute Manipulation.

Facial Attribute Manipulation (FAM) aims to aesthetically modify a given face image to render desired attributes, which has received significant attention due to its broad practical applications ranging from digital entertainment to biometric forensics. In the last decade, with the remarkable success of Generative Adversarial Networks (GANs) in synthesizing realistic images, numerous GAN-based models have been proposed to solve FAM with various problem formulation approaches and guiding information representations. This paper presents a comprehensive survey of GAN-based FAM methods with a focus on summarizing their principal motivations and technical details. The main contents of this survey include: (i) an introduction to the research background and basic concepts related to FAM, (ii) a systematic review of GAN-based FAM methods in three main categories, and (iii) an in-depth discussion of important properties of FAM methods, open issues, and future research directions. This survey not only builds a good starting point for researchers new to this field but also serves as a reference for the vision community.