Nokia Technologies Oy

Huawei Technologies Co., Limited

Nokia Corporation

Alibaba Group Holding Limited

Banma Zhixing Network (Hongkong) Co., Limited

Boe Technology Group Co., Ltd.

Boe (Hebei) Mobile Display Technology Co., Ltd.

Honor Device Co., Ltd.

Provenance Asset Group LLC

Jiangwei Li

Kongqiao Wang

Lei Xu

He Yan

Gang Chen

Yikai Fang

Yingfei Liu

Yongqin Liu

Xueshu Zhong

Tao Wang

Liu Liu

Wei Luo

Xing Zhang

Xin Liu

Zheng Li

Hao Wang

Congchao Zhu

Cheng Du

Jing Hu

Huan Yun Zhang

Sean Moran

Youliang Yan

Tao Xiong

Jun Cao

Yameng Wei

Gregory Gibran Slabaugh

Fenglong Song

Kong Qiao Wang

Kun Liu

Hongbo Min

Vuokko Tuulikki Lantz

Jyri Huopaniemi

Ioannis Marras

Steven George McDonagh

Zhen Wang

Zhongwei Tang

Guiyun Wang

Ioannis Alexiou

Chunlin Qin

Jinlei Zhang

Jiunn Bay

Jose Costa Pereira

Viktor Vladimirovich Smirnov

Wensen Feng

Xiuyan Guo

Li Zeng

Lizhi Xiong

Aihua Zhao

Jimmy Wah Tung Wan

Longqi Chen

Xiaowen You

A visual localization method and apparatus are provided. The method includes obtaining a captured first image, determining a first pose based on the first image and an aerial model, determining whether a ground model corresponding to the first pose exists in an aerial-ground model, and when the ground model corresponding to the first pose exists, determining a second pose based on the ground model. The aerial-ground model includes the aerial model and the ground model mapped to the aerial model, a coordinate system of the ground model is the same as a coordinate system of the aerial model, and localization accuracy of the second pose is higher than localization accuracy of the first pose. Performing fine visual localization based on the ground model can improve accuracy and a success rate of localization.

Visual localization method and apparatus

An image processing method includes segmenting, by a cloud server and based on a zoom ratio of a high-definition image in a high-definition image library, a low-definition image of a small zoom ratio from a terminal to obtain a plurality of image blocks. For each image block, performing, by the cloud server, retrieval and matching in the high-definition image library to obtain one or more high-definition reference images, and then performing, by the cloud server, image quality improvement using an image enhancement network that is based on the high-definition reference images to obtain a plurality of high-definition image blocks. Finally, stitching, by the cloud server, the high-definition image blocks into a super-definition image with higher resolution and higher definition, and returning, by the cloud server, the super-definition image to the terminal.

Image processing method and related apparatus

An image processing apparatus and a method are provided. The apparatus comprises a plurality of processing modules configured to operate in series to refine a raw image captured by a camera, the modules comprising a first module and a second module, each of which independently implements a respective trained artificial intelligence model, wherein: the first module implements an image transformation operation that performs an operation from the set comprising: (i) an essentially pixel-level operation that increases sharpness of an image input to the module, (ii) an essentially pixel-level operation that decreases sharpness of an image input to the module, (iii) an essentially pixel-block-level operation on an image input to the module; and the second module as a whole implements a different operation from the said set.

Image processor and method

A method for playing media data is disclosed, including: transmitting, by a first operating system, a request for processing the media data to a second operating system, the first operating system and the second operating system being installed on a same device; receiving, by the first operating system, processing results from the second operating system, wherein the second operating system is configured to process the media data based at least in part on the request to generate the processing results; and playing the media data by the first operating system based at least in part on the processing results.

Method and system for playing media data

A method, where one file includes file data of a plurality of files for generating a three-dimensional model includes obtaining a first file in a picture format, an extension data segment of the first file includes at least one first data segment, and the first data segment includes the file data of the files for generating a first three-dimensional model of the three-dimensional model, obtaining the file data of the files from the first data segment, and generating the first three-dimensional model based on the file data of the files.

Method for generating three-dimensional model, and terminal device

Playing multimedia data including instructing that a transparent area be painted in a first drawing layer, instructing that a multimedia data playing window be painted in a second drawing layer, the multimedia data playing window overlapping with the transparent area, instructing synchronous display of the transparent area and the playing window, and instructing that the multimedia data be played in the playing window.

Method and system for playing multimedia data

A method includes: obtaining a target zoom ratio; simultaneously photographing a monochrome image and a color image of a target scene based on the target zoom ratio, where resolution of the monochrome image is higher than that of the color image, and there is at least one monochrome image and at least one color image; correspondingly cropping the monochrome image and the color image based on the target zoom ratio, where a field of view corresponding to a monochrome image obtained through cropping is the same as a field of view corresponding to a color image obtained through cropping; and performing fusion on the monochrome image obtained through cropping and the color image obtained through cropping, to obtain a color zoom image.

Photographing method for terminal and terminal

A method for processing multimedia data is disclose, including: determining whether at least one frame associated with the multimedia data has been decoded; in response to the determination that the at least one frame associated with the multimedia data has been decoded, drawing a transparent area on a display interface; and instructing a multimedia data playing window and the at least one frame associated with the multimedia data to be drawn, wherein the transparent area and the multimedia data playing window overlap at different drawing layers.

System and method for streaming multimedia data

A method includes obtaining a to-be-processed current point in a target area in a current frame, obtaining a first-type smoothing weight of a first-type neighborhood point in an Nframe before the current frame with respect to the current point, where the first-type neighborhood point is an Xcircle point that encircles a point corresponding to a location of the current point and that is in the Nframe before the current frame, obtaining a second-type smoothing weight of a second-type neighborhood point in an Mframe after the current frame with respect to the current point, where the second-type neighborhood point is a Ycircle point that encircles the point corresponding to the location of the current point and that is in the Mframe after the current frame, and performing smoothing calculation on the current point according to the first-type smoothing weight and the second-type smoothing weight.

Video smoothing method and apparatus

Rendering video is disclosed including responding to an access request from a video data provider using a first video buffer queue corresponding to a first rendering technique, receiving a request to change the first rendering technique to a second rendering technique, and switching the first video buffer queue for the access request to a second video buffer queue corresponding to the second rendering technique, the first video buffer queue and the second video buffer queue being concurrent.

Method and system for managing buffers

Obtaining a first set including key point descriptors in a first image that is of a to-be-shot scene and that is formed by using a first camera in a dual camera system, and a second set including key point descriptors in a second image that is of the to-be-shot scene and that is formed by using a second; pairing a key point in the first set and a key point in the second set that match each other to form a key point pair; selecting the key point pair that meets a predetermined condition; generating an image alignment vector field according to the selected key point pair; and estimating an occlusion area according to the depth information of the first image and the second image, and eliminating an alignment vector of the occlusion area in the image alignment vector field, to form a corrected image alignment vector field.

Dual camera system and image processing method for eliminating an alignment vector of an occlusion area in an image alignment vector field

Embodiments of the invention provide a recording device, which comprises a recording unit, a management unit and a storage unit, wherein the management unit is arranged to generate an identification code and write the identification code into the storage unit, the storage unit is arranged to store the identification code, and the recording unit is arranged to read the identification code from the storage unit and record the identification code into TFT display module. The recording device can record the unique code for each TFT display module to uniquely distinguish different TFT display modules, thereby facilitating tracking and adjustment of parameters, such as color and the like, of an installed TFT display terminal. On the other hand, the recording device can simplify a large amount of complex marking work, and guarantee that the TFT display modules would not be identified mistakenly while saving manpower and material resources.

Recording device, system and method

It is inter alia disclosed to classify samples of a set of samples of an image regarding whether or not a respective sample comprises optical information on a specific object type based on classification information. Therein, the classification information comprises a plurality of classifiers, each classifier being associated exclusively with one color channel of a plurality of color channels.

Classifying image samples

The invention relates to a method, comprising tracking the gaze of an eye of a user by a first camera, wherein a position of the gaze determines a place for the cursor on the screen of a near-to-eye display (NED), wherein the movement of the gaze is configured to move the cursor on the screen and when the movement of the gaze is detected to be still or moving only slightly; observing a gesture of one hand of the user by a second camera, and executing a further operation if at least one gesture of the hand is detected. The invention further relates to an apparatus and a computer program product configured to perform the method.

Multimodal interaction with near-to-eye display

Embodiments of the present invention relate to a method and apparatus for detecting an imaging condition. In one embodiment, there is provided a method for detecting an imaging condition. The method comprises: determining, based on luminance distribution in a first image of a scene, imaging lightness of the first image, the first image being captured by a first camera; determining, based on detection of a highlighted region in a second image of the scene, imaging exposureness of the second image, the second image being captured by a second camera, the first image and the second image being captured under a same or similar imaging condition, an exposure amount of the first camera being lower than an exposure amount of the second camera. There is also disclosed a relevant apparatus, electronic device, and a computer program product.

Method and apparatus for detecting imaging conditions

Growing community of inventors

Beijing, China

Jiangwei Li