Identity-Aware and Shape-Aware Propagation of Face Editing in Videos.

The development of deep generative models has inspired various facial image editing methods, but many of them are difficult to be directly applied to video editing due to various challenges ranging from imposing 3D constraints, preserving identity consistency, ensuring temporal coherence, etc. To address these challenges, we propose a new framework operating on the StyleGAN2 latent space for identity-aware and shape-aware edit propagation on face videos. In order to reduce the difficulties of maintaining the identity, keeping the original 3D motion, and avoiding shape distortions, we disentangle the StyleGAN2 latent vectors of human face video frames to decouple the appearance, shape, expression, and motion from identity. An edit encoding module is used to map a sequence of image frames to continuous latent codes with 3D parametric control and is trained in a self-supervised manner with identity loss and triple shape losses. Our model supports propagation of edits in various forms: I. direct appearance editing on a specific keyframe, II. implicit editing of face shape via a given reference image, and III. existing latent-based semantic edits. Experiments show that our method works well for various forms of videos in the wild and outperforms an animation-based approach and the recent deep generative techniques.

Human Motion Transfer With 3D Constraints and Detail Enhancement.

We propose a new method for realistic human motion transfer using a generative adversarial network (GAN), which generates a motion video of a target character imitating actions of a source character, while maintaining high authenticity of the generated results. We tackle the problem by decoupling and recombining the posture information and appearance information of both the source and target characters. The innovation of our approach lies in the use of the projection of a reconstructed 3D human model as the condition of GAN to better maintain the structural integrity of transfer results in different poses. We further introduce a detail enhancement net to enhance the details of transfer results by exploiting the details in real source frames. Extensive experiments show that our approach yields better results both qualitatively and quantitatively than the state-of-the-art methods.

One-pot synthesis and property study on thieno[3,2-b]furan compounds.

Based on the regioselective intermolecular Suzuki coupling and subsequent intramolecular Ullmann C-O coupling reactions, one-pot synthesis of benzo[4,5]thieno[3,2-b]benzofurans (BTBFs) was developed after optimization of the reaction conditions including catalysts, solvents, bases, ligands and reaction times. The one-pot reaction, with only 2 mol% Pd(PPh3)4 and 2 mol% copper(i) thiophene-2-carboxylate (CuTc) as the catalysts, K3PO4·3H2O as the base and tert-butanol as the solvent, afforded moderate to good yields (up to 70%) for a variety of substrates.

A genetically engineered Escherichia coli that senses and degrades tetracycline antibiotic residue.

Due to the abuse of antibiotics, antibiotic residues can be detected in both natural environment and various industrial products, posing threat to the environment and human health. Here we describe the design and implementation of an engineered Escherichia coli capable of degrading tetracycline (Tc)-one of the commonly used antibiotics once on humans and now on poultry, cattle and fisheries. A Tc-degrading enzyme, TetX, from the obligate anaerobe Bacteroides fragilis was cloned and recombinantly expressed in E. coli and fully characterized, including its K m and k cat value. We quantitatively evaluated its activity both in vitro and in vivo by UV-Vis spectrometer and LC-MS. Moreover, we used a tetracycline inducible amplification circuit including T7 RNA polymerase and its specific promoter PT7 to enhance the expression level of TetX, and studied the dose-response of TetX under different inducer concentrations. Since the deployment of genetically modified organisms (GMOs) outside laboratory brings about safety concerns, it is necessary to explore the possibility of integrating a kill-switch. Toxin-Antitoxin (TA) systems were used to construct a mutually dependent host-plasmid platform and biocontainment systems in various academic and industrious situations. We selected nine TA systems from various bacteria strains and measured the toxicity of toxins (T) and the detoxifying activity of cognate antitoxins (A) to validate their potential to be used to build a kill-switch. These results prove the possibility of using engineered microorganisms to tackle antibiotic residues in environment efficiently and safely.