Netflix Inc.

Aditya Mavlankar

Mark Watson

Ioannis Katsavounidis

Anush Moorthy

Liwei Guo

Li-Heng Chen

Zhi Li

Christos G Bampis

Anne Aaron

Adithya Prakash

Kyle Christopher Swanson

Loannis Katsavounidis

In various embodiments, a video editing application receives, from an encoding application, a list of random access points of an encoded media content item. When an operator specifies a point of interest for the media content item, the video editing application determines a closest random access point to the point of interest and modifies the point of interest to coincide with the closest random access point. The encoding application can also modify the point of interest to coincide with an existing random access point if the point of interest is within a tolerance of the existing random access point and the point of interest is not frame specific. Further, the encoding application can modify media metrics, computed using pre-encoded versions of the media content item, using heuristics to account for operator-specified points of interest that do not coincide with, or are not within a tolerance of, existing random access points.

Techniques for avoiding re-encoding of media content items

One embodiment of the invention sets forth a mechanism for encoding video streams associated with the same digital content such that switch points staggered across two video streams occur at every offset temporal distance. The offset temporal distance is less than the distance between two consecutive key frames in a given video stream. This enables a content player to switch to a video stream having a playback quality up or down one level from a current video stream at the offset temporal distance from the most recently played key frame. In effect, the content player does not wait the entire key frame temporal distance before switching.

Staggered key frame video encoding

In various embodiments, an encoding ladder application generates encoding ladders for encoding media titles. In operation, the encoding ladder application generates a first convex hull representing encoding tradeoffs between quality and bitrate when encoding a media title at a first resolution; The encoding ladder application generates a second convex hull representing encoding tradeoffs between quality and bitrate when encoding the media title at a second resolution. Based on the first convex hull and the second convex hull, the encoding ladder application generates an overall convex hull. Subsequently, the encoding ladder application generates an encoding ladder for the media title based on at least the overall convex hull and a ladder requirement. Advantageously, the tradeoffs between quality and bitrate represented by the encoding ladder are customized for the media title. Consequently, encoding inefficiencies attributable to conventional fixed-bitrate ladders can be reduced.

Techniques for generating per-title encoding ladders

In various embodiments, a training application trains a machine learning model to preprocess images. In operation, the training application computes a chroma sampling factor based on a downscaling factor and a chroma subsampling ratio. The training application executes a machine learning model that is associated with the chroma sampling factor on data that corresponds to both an image and a first chroma component to generate preprocessed data corresponding to the first chroma component. Based on the preprocessed data, the training application updates at least one parameter of the machine learning model to generate a trained machine learning model that is associated with the first chroma component.

Machine learning techniques for component-based image preprocessing

In various embodiments, a codec comparison application independently encodes each source image included in a set of source images using a first encoding configuration to generate a first set of encoded images. The codec comparison application also independently encodes each source image included in the set of source images using a second encoding configuration to generate a second set of encoded images. For each encoded image in the first set of encoded images and each encoded image in the second set of encoded images, a visual quality score for a reconstructed source image derived from the encoded image falls within a tolerance of a target visual quality score. Subsequently, the codec comparison application computes a bitrate change based on a first total file size for the first set of encoded image and a second total file size for the second set of encoded images

Techniques for comparing the compression efficiency of encoding configurations

In various embodiments, an image encoding application determines a first value for an encoding parameter based on a search interval. The image encoding application then encodes a source image using the first value for the encoding parameter to generate a first encoded image. Subsequently, the image encoding application computes a visual quality score for a first reconstructed source image derived from the first encoded image. The image encoding application reduces the search interval based on a comparison between the visual quality score and the target visual quality score. Based on the resulting reduced search interval, the image encoding application determines a second value for the encoding parameter. The image encoding application encodes the source image using the second value for the encoding parameter to generate a second encoded image. Subsequently, the image encoding application transmits the second encoded image to software application(s) for further processing and display.

Techniques for compressing images to achieve a target quality level

A computer-implemented method includes receiving a request from a client computing device for a first shot included in a media title being streamed to the client computing device for playback; in response to the request, sending the first shot to the client computing device for playback; and sending a representative image for at least one of the first shot and a second shot included in the media title, wherein the first shot comprises a first sequence of video frames that is included in the media title and captured continuously from a first point of capture, and the second shot comprises a second sequence of video frames that is included in the media title and captured continuously from a second point of capture.

Growing community of inventors

San Francisco, CA, United States of America

Aditya Mavlankar