Animation rendering system

Abstract

The invention provides an animation rendering system based on a distributed computer system. The animation rendering system comprises at least one main task node device connected through a computer network and multiple task executing node devices, wherein the main task node devices are configured to divide a rendering task into multiple task units and distributing the task to the executing node devices, and the executing node devices are configured to complete the task units. The invention further provides a rendering method based on cloud computing, namely distributed processing of cloud computing and storage advantages are utilized to divide one or more rendering tasks, rendering is performed through the nodes in a cluster simultaneously, and the purposes of rapidly rendering, shortening the manufacturing time and reducing the cost are achieved.

Description

technical field [0001] The invention relates to the field of animation production, in particular to an animation rendering system. Background technique [0002] We are amazed by the special effects of 3D movies, but behind these cool animation effects, there are extremely complex technical components and massive computing and storage resource consumption, which require very high requirements for both labor and equipment. In terms of data, a well-made special effects movie has a resolution of about 2k-4k per frame, and it takes about 2 hours to process it on a single machine with an 8-core CPU, and it takes 2,800,000 hours to render a whole movie, nearly 300 years , if you want to control the production time within one year, you need 300 machines with the same performance and 300 qualified designers, which shows the high cost threshold. [0003] At the same time, the primary problem facing cloud-based rendering is how to divide a relatively independent and complete rendering...

AI Technical Summary

Problems solved by technology

[0002] The special effects of 3D movies amaze us, but behind these cool animation effects, there are extremely complex technical components and massive computing and storage resource consumption, which require very high requirements for both labor and equipment

There are many ways to split, such as splitting according to animation duration, or splitting according to the number of machines, but these cannot meet the high performance, high efficiency and dynamic scalability of parallel rendering

For example, according to the animation duration, an animation contains different frames per second. A simple scene may only need a few pictures, while a cool scene needs to switch dozens of pictures within 1 second. Therefore, if the animation is divided according to the length of the animation, it will inevitably lead to unbalanced load between nodes and frequent communication

However, evenly dividing according to the number of machines cannot reflect the effect of collaborative operations, and it is no different from hundreds of single-machine executions.

Images