Abstract: Provided are a dual-drug link assembly unit represented by formula III, or a stereoisomer thereof, or an optical isomer thereof. The dual-drug link assembly unit can be linked to a targeting linker to obtain a dual-drug targeting linker-drug conjugate represented by formula I. The specific structure can effectively reduce the aggregation of the dual-drug targeting linker-drug conjugate, which facilitates process scale-up, thereby improving the efficiency of the targeting effect on tumor cells, reducing the toxic and side effects on normal cells, and at the same time, effectively overcoming drug resistance and achieving a synergistic anti-tumor effect. Compared with DS-8201 which is already on the market, the ADC provided by the present invention significantly improves the inhibition effect on HER2 positive cell strains N87 and SK—BR-3d.

Abstract: A method for generating a facial animation from a single image is provided. The method is mainly divided into four steps: generation of facial feature points in an image, global two-dimensional deformation of the image, optimization of details of a facial area, and generation of texture of an oral cavity area. The present disclosure can generate a facial animation in real time according to a change of the facial feature points, and the animation quality reaches a level of current state-of-art facial image animation technology. The present disclosure can be used in a series of applications, such as facial image editing, portrait animation generation based on a single image, and facial expression editing in videos.

Abstract: A method for generating a facial animation from a single image is provided. The method is mainly divided into four steps: generation of facial feature points in an image, global two-dimensional deformation of the image, optimization of details of a facial area, and generation of texture of an oral cavity area. The present disclosure can generate a facial animation in real time according to a change of the facial feature points, and the animation quality reaches a level of current state-of-art facial image animation technology. The present disclosure can be used in a series of applications, such as facial image editing, portrait animation generation based on a single image, and facial expression editing in videos.