After classifying the pixels, the filter generates an eight-bit alpha mask with the same resolution as the input image.Pixels that are part of a human are classified as foreground pixels.Īll other pixels are classified as background pixels. The filter classifies the pixels in the video based on the filter's confidence:.The AI green screen filter processes an input image by performing the following sequence of operations: Refer to Sample Applications Reference for more information about a sample application that you can use to experience this effect. The output of the filter is written to an 8-bit (grayscale) GPU buffer.The input should be provided in a GPU buffer in BGR interleaved format, where each pixel is a 24-bit unsigned char value, and, therefore, 8-bit per pixel component.The filter works on images with other aspect ratios. Some degradation in quality may be observed.įor best results, the aspect ratio of the image file must be 16:9. Performance mode, which gives the fastest performance.Images must be at least 288 pixels high and at least 512 pixels wide.Quality mode, which gives the highest quality result.The following modes of operation are supported: The AI green screen filter segments a video or still image into foreground and background regions. To learn more about how to get started with Maxine and how to install the SDK, refer to the Video Effects SDK System Guide. This section provides information about the effects in the NVIDIA® Video Effects SDK.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |