Real-time precoding content adaptive GPU image dithering

Real-time precoding dithering techniques mitigate or eliminate banding and other graphics artifacts in video frames before the video frames are encoded for transmission to and displayed by one or more client devices. For each of one or more input video frames, a frame identifier and one or more random seeds are received, and a dithering process is initiated for each of one or more pixels of the input video frame. The dithering process includes generating a YUV noise vector based on a random seed and a frame identifier, calculating a YUV representation of the input pixel based on RGB color information of the input pixel, and generating a dithered output pixel by adding the generated YUV noise vector to the YUV representation of the input pixel. 实时预编码抖动技术在视频帧被编码以传输到一个或多个客户端设备并且由一个或多个客户端设备显示之前减轻或消除这样的视频帧中的条带和其他图形伪影。对于一个或多个输入视频帧中的每一个，接收帧标识符和一个或多个随机种子，并且抖动进程针对输入视频帧的一个或多个像素中的每一个来发起。抖动进程包括基于随机种子和帧标识符来生成YUV噪声向量、基于输入像素的RGB颜色信息来计算输入像素的YUV表示、以及通过添加所生成的YUV噪声向量到输入像素的YUV表示来生成抖动输出像素。