Bigo Technology Pte. Ltd.

Leju Yan

Qing Liu

Li Liu

Gengdai Liu

Feiqian Zhang

Yue Ma

Xinning Wang

Provided is a method for encoding video data. The method includes: acquiring video data; configuring an encoding parameter of an encoder; determining a first time interval between two adjacent video frames in a group of pictures based on the encoding parameter; and adjusting a number of video frames in the group of pictures based on the first time interval by encoding the video data based on the encoding parameter. A device and a storage medium are also provided.

Method for encoding video data, device, and storage medium

An illumination detection method comprises acquiring a face image to be detected and a three-dimensional face mesh template; deforming the three-dimensional face mesh template according to the face image to obtain a reconstructed face mesh model; according to the deformation positions, in the reconstructed face mesh model, of key feature points in the three-dimensional face mesh template, determining the brightness of feature points, corresponding to the key feature points, in the face image; and according to the relationship between the predetermined brightness of the key feature points and the illumination, and the brightness of the feature points, corresponding to the key feature points, in the face image, determining illumination information of the face image.

Illumination detection method and apparatus for face image, and device and storage medium

Provided are a method, apparatus and device for adding a video special effect and a storage medium. The method includes: acquiring a source video sequence and at least one special effect video sequence; in the case where frame rates of the two or more than two special effect video sequences are same, inserting a frame into the source video sequence and superimposing the two or more than two special effect video sequences on the source video sequence at the same time; and in the case where frame rates of the two or more than two special effect video sequences are different, determining a target frame rate from the frame rates of the two or more than two special effect video sequences inserting frames into the source video sequence and then superimposing the two or more than two special effect video sequences on the source video sequence.

Method, device and apparatus for adding video special effects and storage medium

The video sending method includes: acquiring a video stream to be transmitted; generating consecutive frame groups from the video stream, wherein setting a first frame in the current frame group to be a long-term reference frame that uses a first frame in a previous frame group as a reference during generation of at least one of the current frame group, wherein the long-term reference frame is a predictive coded frame configured to transmit a difference and a motion vector obtained by performing a comparison against the first frame in the previous frame group, the current frame group is a frame group other than the first frame group; and sending the frame groups to a receiving terminal. The video receiving method comprises: receiving the frame groups sent by a sending terminal; and restoring the frame groups to obtain the transmitted video stream.

Growing community of inventors

Guangzhou, China

Leju Yan