Tencent Technology (shenzhen) Company Limited

Huawei Technologies Co., Limited

Tencent Technology Company Limited

Jiaya Jia

Xiaoyong Shen

Yuwing Tai

Chen Li

Shu Liu

Xin Tao

Ruiyu Li

Wenjie Pei

Hong Zhang

Li Jiang

Yi Tong Wang

Li Xu

Yi Wang

Lei Ke

Zhicheng Yang

Yu Wing Tai

Weilong Peng

Pengyuan Lv

Hongwei Yi

Yilun Chen

Chong Sun

Huchuan Lu

Lu Qi

Ruizheng Wu

Hongyun Gao

Jiyuan Zhang

Xiangrong Wang

Zhaoyang Yang

Xinhang Leng

Ruixing Wang

Xinlong Wang

Yuxuan Sun

Qiong Cao

Shuang Sun

Liying Lu

Kwokwai Hung

A method for training an SMPL parameter prediction model, including: obtaining a sample picture; inputting the sample picture into a pose parameter prediction model to obtain a predicted pose parameter; inputting the sample picture into a shape parameter prediction model to obtain a predicted shape parameter; calculating model prediction losses according to an SMPL parameter prediction model and annotation information of the sample picture; and updating the pose parameter prediction model and the shape parameter prediction model according to the model prediction losses.

Method for training SMPL parameter prediction model, computer device, and storage medium

An image processing method includes: obtaining an image, and performing feature extraction on the image; generating at least one candidate region of the image, and mapping the at least one candidate region into a feature map of the image, one candidate region including one instance; processing the mapped feature map based on a target network for instance segmentation; and indicating an overall structure of an occluded instance in the image by using a perspective mask, and indicating an invisible part of the occluded instance by using a non-perspective mask, the perspective mask and the non-perspective mask representing a relative occlusion relationship of the occluded instance.

Image processing method, apparatus, and device, and storage medium

The present disclosure provides a target image generation method. The method includes obtaining a first parsed image and a first pose image based on an original image, the first parsed image being an image labeled with parts of an object in the original image, the first pose image representing a pose of the object in the original image; inputting the first parsed image, the first pose image, and a second pose image representing a target pose into a first image generation model, and determining, a first transformation parameter and adjusting the first parsed image based on the first transformation parameter to obtain a target parsed image, a pose of the object in the target parsed image being the target pose; and inputting a first combined image and a second combined image into a second image generation model, and adjusting the first combined image to obtain a target image.

Target image generation method and apparatus, server, and storage medium

A computer device extracts an image feature of an image that includes one or more characters to be recognized. The image feature includes a plurality of image feature vectors. The device uses an attention mechanism to compute and output attention weight values corresponding to the target number of characters, based on the image feature vectors, through parallel computing. Each of the attention weight values corresponds to one or more respective characters and represents an importance of the plurality of image feature vectors for the respective characters. The device obtains at least one character according to the plurality of image feature vectors and the target number of attention weight values. Therefore, in a character recognition process, with recognition based on the foregoing attention mechanism, a character in any shape can be effectively recognized by using a simple procedure, thereby avoiding a cyclic operation process and greatly improving operation efficiency.

Character recognition method and apparatus, computer device, and storage medium

This application discloses an image processing method, device, and apparatus, and a storage medium. The method is performed by a computing device, the method including: receiving an input image; determining a context feature of the input image; determining a first feature set and a second feature set according to the context feature and based on a size of a target image and a location of the input image in the target image; adjusting the second feature set according to a first feature statistic of the first feature set, to obtain an adjusted second feature set; and generating the target image based on the adjusted second feature set and the first feature set.

Image processing method and apparatus, device, and storage medium

The present disclosure provides an image processing method and apparatus, and an electronic device, and relates to the field of artificial intelligence (AI). The method includes: obtaining an input image and extracting region features of image regions in the input image to obtain a first image feature; processing pixels in the first image feature according to a predetermined rule, and determining a second image feature according to the processed pixels; and determining, based on the second image feature and at least one word vector that is determined for the input image, word vectors corresponding to the region features of the image regions in the first image feature at different moments, predicting positions of the word vectors in a text description, and forming the text description corresponding to the input image according to the word vectors and the positions.

Image processing method and apparatus, and storage medium

This application relates to a point cloud segmentation method, a computer-readable storage medium, and a computer device. The method includes encoding a to-be-processed point cloud to obtain a shared feature, the shared feature referring to a feature shared at a semantic level and at an instance level; decoding the shared feature to obtain a semantic feature and an instance feature respectively; adapting the semantic feature to an instance feature space and fusing the semantic feature with the instance feature, to obtain a semantic-fused instance feature of the point cloud, the semantic-fused instance feature representing an instance feature fused with the semantic feature; dividing the semantic-fused instance feature of the point cloud, to obtain a semantic-fused instance feature of each point in the point cloud; and determining an instance category to which each point belongs according to the semantic-fused instance feature of each point.

Point cloud segmentation method, computer-readable storage medium, and computer device

Embodiments of this disclosure include an image enhancement method and apparatus. The image enhancement may include obtaining an original image and performing synthesis processing on features of the original image to obtain a first illumination map corresponding to the original image. A resolution of the first illumination map may be lower than a resolution of the original image. The image enhancement may further include obtaining, based on the first illumination map, a mapping relationship between an image to an illumination map and performing mapping processing on the original image based on the mapping relationship to obtain a second illumination map. A resolution of the second illumination map may be equal to the resolution of the original image. The image enhancement may further include performing image enhancement processing on the original image according to the second illumination map to obtain a target image.

Image enhancement method and apparatus, and storage medium

A gesture language recognition method is provided. In the method, a first video is obtained. Gesture features are extracted from frames of images in the first video. Gesture change features are extracted from the frames of the images in the first video. Gesture language word information is extracted from fused features that are determined based on the gesture features and the gesture change features. The gesture language word information is combined into a gesture language sentence according to context information corresponding to the gesture language word information.

Gesture language recognition method and apparatus, computer-readable storage medium, and computer device

Embodiments of this application disclose a training method using image processing model for processing blurry images. The method includes obtaining a sample pair comprising a clear image and a corresponding blurry image; the sharpness of the clear image being greater than a preset threshold, the sharpness of the blurry image being less than the preset threshold; activating the image processing model to perform sharpness restoration on the blurry image to obtain a restored image; and updating network parameters of a first network and network parameters of a second network in the image processing model according to the restored image and the clear image to obtain a trained image processing model; the network parameters of the first network and the network parameters of the second network meeting a selective sharing condition indicating whether the network parameters between the first network and the second network are shared or independent.

Training method for image processing model, image processing method, network device, and storage medium

A video caption generating method is provided to a computer device. The method includes encoding a target video by using an encoder of a video caption generating model, to obtain a target visual feature of the target video, decoding the target visual feature by using a basic decoder of the video caption generating model, to obtain a first selection probability corresponding to a candidate word, decoding the target visual feature by using an auxiliary decoder of the video caption generating model, to obtain a second selection probability corresponding to the candidate word, a memory structure of the auxiliary decoder including reference visual context information corresponding to the candidate word, determining a decoded word in the candidate word according to the first selection probability and the second selection probability, and generating a video caption according to decoded word.

Video caption generating method and apparatus, device, and storage medium

A method and apparatus for labelling information of a video frame, includes: obtaining a video; performing feature extraction on a target video frame in the video, to obtain a target image feature of the target video frame; determining, according to image feature matching degrees between the target video frame and labelled video frames, a guide video frame of the target video frame from the labelled video frames, the guide video frame being used for guiding the target video frame for information labelling, and the image feature matching degrees being matching degrees between the target image feature and image features corresponding to the labelled video frames; and generating target label information corresponding to the target video frame according to label information corresponding to the guide video frame.

Method and apparatus for labelling information of video frame, device, and storage medium

This application provides a target tracking method, including: obtaining a plurality of consecutive picture frames of a target video, and setting a tracked target region of an npicture frame; performing a feature extraction operation on the tracked target region of the npicture frame, to obtain a feature map of the tracked target region; calculating a weighted filter corresponding to the input feature map according to a correlation filter algorithm and a mean pooling constraint condition; calculating an output response of an (n+1)picture frame by using the weighted filter and an input feature map of the (n+1)picture frame in the plurality of consecutive picture frames, and determining a tracked target region of the (n+1)picture frame according to the output response of the (n+1)picture frame, until tracked target regions of all the consecutive picture frames are obtained. This application improves precision and effectiveness of target tracking.

Target tracking method and apparatus, storage medium, and electronic device

Embodiments of this application disclose a method and an apparatus for reconstructing a three-dimensional model of a human body, and a storage medium. The method includes obtaining a two-dimensional image of a human body part to be reconstructed; mapping the two-dimensional image to a voxel space, to obtain a voxelized result of the two-dimensional image; obtaining three-dimensional morphable model parameters corresponding to the two-dimensional image based on calculating the voxelized result using a preset three-dimensional parameter regression network; and reconstructing a three-dimensional model of the human body part based on the three-dimensional morphable model parameters.

Method and apparatus for reconstructing three-dimensional model of human body, and storage medium

A human pose prediction method is provided for an electronic device. The method includes using a basic neural network based on image-feature-based prediction to perform prediction on an inputted target image, to obtain an initial prediction map of a human key-point; inputting the initial prediction map of the human key-point and a human structure diagram into a pose graph neural network based on spatial information mining, each node in the human structure diagram corresponding to a human joint respectively, and each edge connecting adjacent human joints; using the pose graph neural network to initialize the human structure diagram by using the initial prediction map of the human key-point, to obtain an initialized human structure diagram; and using the pose graph neural network to perform iterative prediction on the initialized human structure diagram, to obtain a final prediction map, the final prediction map indicating a predicted human pose.

Growing community of inventors

Shenzhen, China

Jiaya Jia