Beijing Didi Infinity Technology and Development Co., Ltd.

Chengxiang Yin

Jian Tang

Kun Wu

Zhengping Che

Bo Jiang

The present disclosure relates to a system and a method for performing instance segmentation based on semantic segmentation that is capable of (1) processing HD images in real-time given semantic segmentation; 2) delivering comparable performance with Mask R-CNN in terms of accuracy when combined with a widely-used semantic segmentation method (such as DPC), while consistently outperforms a state-of-the-art real-time solution; (3) working flexibly with any semantic segmentation model for instance segmentation; (4) outperforming Mask R-CNN if the given semantic segmentation is sufficiently good; and (5) being easily extended to panoptic segmentation.

Systems and methods for instance segmentation based on semantic segmentation

Embodiments of the disclosure provide systems and methods for performing motion transfer using a learning model. An exemplary system may include a communication interface configured to receive a first image including a first movable object and a second image including a second movable object. The system may also include at least one processor coupled to the communication interface. The at least one processor may be configured to extract a first set of motion features of the first movable object from the first image using a first encoder of the learning model and extract a first set of static features of the second movable object from the second image using a second encoder of the learning model. The at least one processor may also be configured to generate a third image by synthesizing the first set of motion features and the first set of static features.

Growing community of inventors

Beijing, China

Chengxiang Yin