Beijing Xiaomi Pinecone Electronics Co., Ltd.

Beijing Xiaomi Mobile Software Co., Ltd.

Beijing Xiaomi Intelligent Technology Co., Ltd.

Binglin Chang

Zhenghui Shi

Qingmin Wang

Kailun Ma

Xingsheng Lin

Xiaojun Wu

Yutong Zang

A method, apparatus, and a non-transitory computer-readable storage medium for processing a video are provided. A terminal determines a subject region of a video frame in a video and a background region. A target object is located in the subject region. The background region is a region of the video frame other than the subject region. The terminal overlays the subject region in at least one of a first video frame having the target object on at least one of a second video frame having the target object and generates a special effect frame including at least two subject regions in each of which the target object is located.

Method and device for processing video, and storage medium

A method for processing a video includes: identifying a target object in a first video segment; acquiring a current video frame of a second video segment; acquiring a first image region corresponding to the target object in a first target video frame of the first video segment, and acquiring a second image region corresponding to the target object in the current video frame of the second video segment, wherein the first target video frame corresponds to the current video frame of the second video segment in terms of video frame time; and performing picture splicing on the first target video frame and the current video frame of the second video segment according to the first image region and the second image region to obtain a processed first video frame.

Method and apparatus for processing video, and storage medium

The present disclosure relates to a video processing method and apparatus, and a storage medium. The method is applied to a terminal and includes: a background frame for a time static special effect is determined from video frames in a video to be processed; for each of the video frames in the video, an image area, where a target object is located is acquired from the respective video frame and the image area is fused into the background frame to generate a special effect frame with the time static special effect.

Video processing method, apparatus and storage medium

A method for multi-exposure photography includes: receiving a screen touch operation, and determining a collected frame corresponding to the screen touch operation, a subject area image corresponding to the screen touch operation, and an alignment parameter of the subject area image corresponding to the screen touch operation; acquiring a currently collected frame in real time; synthesizing the subject area image corresponding to the screen touch operation, or the subject area image corresponding to the screen touch operation together with subject area images corresponding to all historical screen touch operations into the currently collected frame according to corresponding alignment parameters, taking the synthesized image to be an image with a multi-exposure processed effect and displaying the image with the multi-exposure processed effect; and taking an image with a multi-exposure processed effect generated after a final screen touch operation to be a multi-exposed result image.

Method and apparatus for multi-exposure photography, and storage medium

A method includes: acquiring a second initial pose according to obstacle region information and geometric scale information of an indoor architectural structure drawing and a first initial pose; acquiring a first feature point location, a locating error and a first pose through a VSLAM algorithm during movement; acquiring a second pose according to the first pose, first initial pose and second initial pose; acquiring a distance to an obstacle according to the second pose, indoor architectural structure drawing and a ray casting algorithm; acquiring a third pose according to the distance, first feature point location, locating error, first pose and a filtering algorithm; acquiring a second feature point location according to the third pose and VSLAM algorithm; and creating an indoor environment map according to the second feature point location and a key frame set.

Method and device for creating indoor environment map

A method for displaying an image includes: receiving a setting instruction for performing upper layer display on an image of a target real object; determining image range information of the image of the target real object in a scene image frame upon the scene image frame is captured; acquiring the image of the target real object in the scene image frame based on the image range information; and setting an image of a preset target virtual object on an upper layer of the scene image frame, and setting the image of the target real object on an upper layer of the image of the target virtual object and the scene image frame based on the image range information.

Growing community of inventors

Beijing, China

Binglin Chang