Abstract: In various embodiments, a training application generates a trained perceptual quality model that estimates perceived video quality for reconstructed video. The training application computes a pixels-per-degree value based on a normalized viewing distance and a display resolution. The training application computes a set of feature values corresponding to a set of visual quality metrics based on a reconstructed video sequence, a source video sequence, and the pixels-per-degree value. The training application executes a machine learning algorithm on the first set of feature values to generate the trained perceptual quality model. The trained perceptual quality model maps a particular set of feature values corresponding to the set of visual quality metrics to a particular perceptual quality score.

Abstract: In various embodiments, a quality inference application estimates perceived video quality for reconstructed video. The quality inference application computes a set of feature values corresponding to a set of visual quality metrics based on a reconstructed frame, a source frame, a display resolution, and a normalized viewing distance. The quality inference application executes a trained perceptual quality model on the set of feature values to generate a perceptual quality score that indicates a perceived visual quality level for the reconstructed frame. The quality inference application performs one or more operations associated with an encoding process based on the perceptual quality score.

Abstract: In various embodiments, a training application trains a convolutional neural network to downsample images in a video encoding pipeline. The convolution neural network includes at least two residual blocks and is associated with a downsampling factor. The training application executes the convolutional neural network on a source image to generate a downsampled image. The training application then executes an upsampling algorithm on the downsampled image to generate a reconstructed image having the same resolution as the source image. The training application computes a reconstruction error based on the reconstructed image and the source image. The training application updates at least one parameter of the convolutional neural network based on the reconstruction error to generate a trained convolutional neural network.

Abstract: In various embodiments, an image preprocessing application preprocesses images. To preprocess an image, the image preprocessing application executes a trained machine learning model on first data corresponding to both the image and a first set of components of a luma-chroma color space to generate first preprocessed data. The image preprocessing application executes at least a different trained machine learning model or a non-machine learning algorithm on second data corresponding to both the image and a second set of components of the luma-chroma color space to generate second preprocessed data. Subsequently, the image preprocessing application aggregates at least the first preprocessed data and the second preprocessed data to generate a preprocessed image.

Abstract: In various embodiments a training application trains convolutional neural networks (CNNs) to reduce reconstruction errors. The training application executes a first CNN on a source image having a first resolution to generate a downscaled image having a second resolution. The training application executes a second CNN on the downscaled image to generate a reconstructed image having the first resolution. The training application computes a reconstruction error based on the reconstructed image and the source image. The training application updates a first learnable parameter value included in the first CNN based on the reconstruction error to generate at least a partially trained downscaling CNN. The training application updates a second learnable parameter included in the second CNN based on the reconstruction error to generate at least a partially trained upscaling CNN.

Abstract: In various embodiments an endpoint application reconstructs downscaled videos. The endpoint application accesses metadata associated with a portion of a downscaled video that has a first resolution and was generated using a trained downscaling convolutional neural network (CNN). The endpoint application determines, based on the metadata, an upscaler that should be used when upscaling the portion of the downscaled video. The endpoint application executes the upscaler on the portion of the downscaled video to generate a portion of a reconstructed video that is accessible for playback and has a second resolution that is greater than the first resolution.

Abstract: 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.

Abstract: In various embodiments, a training application generates a perceptual video model. The training application computes a first feature value for a first feature included in a feature vector based on a first color component associated with a first reconstructed training video. The training application also computes a second feature value for a second feature included in the feature vector based on a first brightness component associated with the first reconstructed training video. Subsequently, the training application performs one or more machine learning operations based on the first feature value, the second feature value, and a first subjective quality score for the first reconstructed training video to generate a trained perceptual quality model. The trained perceptual quality model maps a feature value vector for the feature vector to a perceptual quality score.

Abstract: In various embodiments, a quality inference application estimates the perceived quality of reconstructed videos. The quality inference application computes a first feature value for a first feature included in a feature vector based on a color component associated with a reconstructed video. The quality inference application also computes a second feature value for a second feature included in the feature vector based on a brightness component associated with the reconstructed video. Subsequently, the quality inference application computes a perceptual quality score based on the first feature value and the second feature value. The perceptual quality score indicates a level of visual quality associated with at least one frame included in the reconstructed video.

Abstract: A computer-implemented method, system and computer program product for compressing video. A set of video frames is partitioned into two subsets of different types of frames, a first type and a second type. The first type of frames of videos is compressed to generate a first representation by a first stage encoder. The first representation is then decoded to reconstruct the first type of frames using a first stage decoder. The second type of frames of video is compressed to generate a second representation that only contains soft edge information by a second stage encoder. A generative model corresponding to a second stage decoder is then trained using the first representation and the reconstructed first type of frames by using a discriminator employed by a machine learning system. After training the generative model, it generates reconstructed first and second types of frames using the soft edge information.

Abstract: A computer-implemented method, system and computer program product for compressing video. A set of video frames is partitioned into two subsets of different types of frames, a first type and a second type. The first type of frames of videos is compressed to generate a first representation by a first stage encoder. The first representation is then decoded to reconstruct the first type of frames using a first stage decoder. The second type of frames of video is compressed to generate a second representation that only contains soft edge information by a second stage encoder. A generative model corresponding to a second stage decoder is then trained using the first representation and the reconstructed first type of frames by using a discriminator employed by a machine learning system. After training the generative model, it generates reconstructed first and second types of frames using the soft edge information.

Abstract: In various embodiments, a training application trains a convolutional neural network to downsample images in a video encoding pipeline. The convolution neural network includes at least two residual blocks and is associated with a downsampling factor. The training application executes the convolutional neural network on a source image to generate a downsampled image. The training application then executes an upsampling algorithm on the downsampled image to generate a reconstructed image having the same resolution as the source image. The training application computes a reconstruction error based on the reconstructed image and the source image. The training application updates at least one parameter of the convolutional neural network based on the reconstruction error to generate a trained convolutional neural network.

Abstract: In various embodiments, a quality inference application estimates the perceived quality of reconstructed videos. The quality inference application computes a first feature value for a first feature included in a feature vector based on a color component associated with a reconstructed video. The quality inference application also computes a second feature value for a second feature included in the feature vector based on a brightness component associated with the reconstructed video. Subsequently, the quality inference application computes a perceptual quality score based on the first feature value and the second feature value. The perceptual quality score indicates a level of visual quality associated with at least one frame included in the reconstructed video.

Abstract: In various embodiments, a training application generates a perceptual video model. The training application computes a first feature value for a first feature included in a feature vector based on a first color component associated with a first reconstructed training video. The training application also computes a second feature value for a second feature included in the feature vector based on a first brightness component associated with the first reconstructed training video. Subsequently, the training application performs one or more machine learning operations based on the first feature value, the second feature value, and a first subjective quality score for the first reconstructed training video to generate a trained perceptual quality model. The trained perceptual quality model maps a feature value vector for the feature vector to a perceptual quality score.

Abstract: A computer-implemented method, system and computer program product for compressing video. A set of video frames is partitioned into two subsets of different types of frames, a first type and a second type. The first type of frames of videos is compressed to generate a first representation by a first stage encoder. The first representation is then decoded to reconstruct the first type of frames using a first stage decoder. The second type of frames of video is compressed to generate a second representation that only contains soft edge information by a second stage encoder. A generative model corresponding to a second stage decoder is then trained using the first representation and the reconstructed first type of frames by using a discriminator employed by a machine learning system. After training the generative model, it generates reconstructed first and second types of frames using the soft edge information.

Abstract: Techniques are provided for fusion of image frames to generate panoramic background images using color and depth data provided from a 3D camera. An example system may include a partitioning circuit configured to partition an image frame into segments and objects, the segments comprising a group of pixels sharing common features associated with the color and depth data, the objects comprising one or more related segments. The system may also include an object consistency circuit configured to assign either 2D or 3D transformation types to each of the segments and objects to transform them to a co-ordinate system of a reference image frame. The system may further include a segment recombination circuit to combine the transformed objects and segments into a transformed image frame and an integration circuit to integrate the transformed image frame with the reference image frame to generate the panoramic image.

Abstract: Techniques are provided for fusion of image frames to generate panoramic background images using color and depth data provided from a 3D camera. An example system may include a partitioning circuit configured to partition an image frame into segments and objects, the segments comprising a group of pixels sharing common features associated with the color and depth data, the objects comprising one or more related segments. The system may also include an object consistency circuit configured to assign either 2D or 3D transformation types to each of the segments and objects to transform them to a co-ordinate system of a reference image frame. The system may further include a segment recombination circuit to combine the transformed objects and segments into a transformed image frame and an integration circuit to integrate the transformed image frame with the reference image frame to generate the panoramic image.