Beijing Zitiao Network Technology Co., Ltd.

Guidong Wang

Tao Wu

Zhendong Qiao

Yunfei Fan

The present disclosure provides a picture rendering method and apparatus, the method comprising: determining a plurality of predicted moments after a current moment, wherein the plurality of predicted moments comprise a plurality of intermediate moments and a display moment after the plurality of intermediate moments; inputting the plurality of predicted moments into a pre-trained prediction model for prediction processing to obtain a plurality of predicted inertial measurement data that correspond to the predicted moments on a one-to-one basis; obtaining a current pose and a current speed of the head-mounted display device, and determining a display pose at the display moment based on the current pose, the current speed and the plurality of predicted inertial measurement data; and rendering a virtual scene based on the display pose to obtain a display picture corresponding to the display moment.

Picture rendering method and apparatus

Embodiments of the present disclosure provide an image processing method and apparatus, a device, a medium and a product. The method is applied to a head-mounted device, where the head-mounted device includes a first camera set to be in a rolling shutter mode and a second camera set to be in a global shutter mode, and the method includes: obtaining a first image acquired by the first camera and a second image acquired by the second camera; obtaining target gain information between the second image and the first image by performing image difference analysis on the first image and the second image; obtaining a target frequency domain image by using the target gain information to repair the first image in a frequency domain; obtaining a target image corresponding to the first image by converting the target frequency domain image from the frequency domain to a time domain.

Growing community of inventors

Beijing, China

Guidong Wang