Alibaba Group Holding Limited

Alibaba Damo (Hangzhou) Technology Co., Ltd.

Chang Zhou

Haohui Xu

Kaiyan Chu

Guibin Lu

Cao Shen

Jingren Zhou

Jie Liu

Wenfei Jiang

Dawei Mei

Huiling Zhou

Shuai Bai

Zhikang Li

Jinbao Xue

Hongxia Yang

Embodiments of this application provide an image generation system and method. In an exemplary manufacturing industry scenario, a style requirement of a product category in a manufacturing industry is automatically captured according to user behavior data and product description information associated with the product category. Based on these data, a style description text may be generated and converted to product images by using a text prediction-based image generation model. The product images are further screened by using an image-text matching model, to obtain a product image with high quality. This process covers from style description text mining to text-to-image prediction to image quality evaluation. It provides an automation product image generation capability for the manufacturing industry, shorten a cycle of designing and producing the product image in the manufacturing industry, and improve production efficiency of the product image.

Image generation system and method

The present disclosure provides methods, apparatuses and systems for transcoding a video. One exemplary method for transcoding a video includes: receiving a model file issued by a machine learning framework; converting the model file to a file identifiable by a filter; setting one or more filtering parameters according to the file; and processing the video based on the filtering parameters. According to the embodiments of the present disclosure, no extra storage will be consumed in the process of video transcoding, and system resource consumption can be reduced without adding any extra system deployment costs.

Methods, apparatuses, and systems for transcoding a video

This application discloses methods and apparatuses for intra prediction mode selection, one method comprising: acquiring a gradient amplitude and a gradient angle of each element in a prediction block; analyzing statistics on the gradient angles and generating a gradient angle histogram of the prediction block; if the texture smoothness of the prediction block is greater than a first pre-determined threshold value, determining that the prediction block is a first-type prediction block, and setting a prediction mode of the first-type prediction block to comprise a direct current prediction mode and a planar prediction mode; and if the texture smoothness of the prediction block is less than a second pre-determined threshold value, determining that the prediction block is a second-type prediction block, and setting an angular prediction mode of the second-type prediction block to comprise an angular prediction mode corresponding to the maximum peak value in the gradient angle histogram.

Rapid selection method for video intra prediction mode and apparatus thereof

A method, an apparatus and a coder for selecting an optimal reference frame in HEVC coding are disclosed. The method includes obtaining optimal reference frames of prediction units spatially adjacent to a current prediction unit, and determining an optimal reference frame of the current prediction unit based on a correlation between optimal reference frames of the spatially adjacent prediction units in a same layer depth for prediction unit(s) of a minimum layer depth. In this way, an ergodic rate distortion cost calculation is not needed to be performed at least for the prediction unit(s) of the minimum layer depth, and the corresponding optimal reference frame is directly determined using the correlation, thus reducing the amount of calculations and enhancing the coding efficiency.

Method, apparatus and coder for selecting optimal reference frame in HEVC coding

Growing community of inventors

Hangzhou, China

Chang Zhou