Abstract: In one embodiment, a method includes determining characteristics of one or more areas in an image by analyzing pixels in the image, computing a sampling density for each of the one or more areas in the image based on the characteristics of the one or more areas, generating samples corresponding to the image by sampling pixels in each of the one or more areas according to the associated sampling density, and providing the samples to a machine-learning model as an input, where the machine-learning model is configured to reconstruct the image by processing the samples.

Abstract: In one embodiment, a method includes accessing a pair of stereo images for a scene, where each image of the pair of stereo images has incomplete pixel information and k channels, stacking the pair of stereo images to form a stacked input image with 2k channels, processing the stacked input image using a machine-learning model to generate a stacked output image with 2k channels, and separating the stacked output image with 2k channels into a pair of reconstructed stereo images for the scene, where each image of the pair of reconstructed stereo images has complete pixel information and k channels.

Abstract: In one embodiment, a computing system may access a video including a first frame and a second frame. The computing system may determine first sampling locations for the first frame and determine second sampling locations for the second frame by transforming the first sampling locations to the second frame according to an optical flow between the first frame and the second frame. The computing system may detect one or more invalid second sampling locations based on determining pixels in the first frame corresponding to the first sampling locations do not match pixels in the second frame corresponding to the second sampling locations. The computing system may reject the one or more invalid second sampling locations to determine third sampling locations for the second frame. The computing system may generate a sample of the video.

Abstract: In one embodiment, a method includes projecting a source image onto a surface using a lens approximation component, where the surface is associated with sampling points approximating photoreceptors of an eye, where each sampling point has a corresponding photoreceptor type, sampling color information from the projected source image at the sampling points, where the color information sampled at each sampling point depends on the corresponding photoreceptor type, accessing pooling units approximating retinal ganglion cells (RGCs) of the eye, where each pooling unit is associated with groups of one or more of the sampling points, calculating weighted aggregations of the sampled color information associated with the groups of one or more sampling points associated with each pooling unit, and computing a perception profile for the source image based on the weighted aggregations associated with each of the pooling units.

Abstract: In one embodiment, a computing system may access a video including a first frame and a second frame. The computing system may determine first sampling locations for the first frame and determine second sampling locations for the second frame by transforming the first sampling locations to the second frame according to an optical flow between the first frame and the second frame. The computing system may select a subset of the second sampling locations based on a comparison between pixels in the first frame corresponding to the first sampling locations and pixels in the second frame corresponding to the second sampling locations. The computing system may define one or more rejection areas in the second frame based on the subset of the second sampling locations to determine third sampling locations in areas outside of the rejection areas. The computing system may generate a sample of the video.

Abstract: In one embodiment, a computing system may receive a video including a sequence of frames. The computing system may access a three-dimensional mask that specifies pixel-sampling locations, the three-dimensional mask having a first dimension and a second dimension corresponding to a spatial domain and a third dimension corresponding to a temporal domain. Blue noise property may be present in the pixel-sampling locations that are associated with each of a plurality of two-dimensional spatial slices of the three-dimensional mask in the spatial domain and the pixel-sampling locations that are associated with each of a plurality of one-dimensional temporal slices of the three-dimensional mask in the temporal domain. The computing system may generate a sample of the video by sampling the sequence of frames using the three-dimensional mask.

Abstract: In one embodiment, a method includes projecting a source image onto a surface using a lens approximation component, where the surface is associated with sampling points approximating photoreceptors of an eye, where each sampling point has a corresponding photoreceptor type, sampling color information from the projected source image at the sampling points, where the color information sampled at each sampling point depends on the corresponding photoreceptor type, accessing pooling units approximating retinal ganglion cells (RGCs) of the eye, where each pooling unit is associated with groups of one or more of the sampling points, calculating weighted aggregations of the sampled color information associated with the groups of one or more sampling points associated with each pooling unit, and computing a perception profile for the source image based on the weighted aggregations associated with each of the pooling units.

Abstract: In one embodiment, a computing system may receive a video including a sequence of frames. The computing system may access a three-dimensional mask that specifies pixel-sampling locations, the three-dimensional mask having a first dimension and a second dimension corresponding to a spatial domain and a third dimension corresponding to a temporal domain. Blue noise property may be present in the pixel-sampling locations that are associated with each of a plurality of two-dimensional spatial slices of the three-dimensional mask in the spatial domain and the pixel-sampling locations that are associated with each of a plurality of one-dimensional temporal slices of the three-dimensional mask in the temporal domain. The computing system may generate a sample of the video by sampling the sequence of frames using the three-dimensional mask.

Abstract: In one embodiment, a computing system may access a video including a first frame and a second frame. The computing system may determine first sampling locations for the first frame and determine second sampling locations for the second frame by transforming the first sampling locations to the second frame according to an optical flow between the first frame and the second frame. The computing system may select a subset of the second sampling locations based on a comparison between pixels in the first frame corresponding to the first sampling locations and pixels in the second frame corresponding to the second sampling locations. The computing system may define one or more rejection areas in the second frame based on the subset of the second sampling locations to determine third sampling locations in areas outside of the rejection areas. The computing system may generate a sample of the video.

Abstract: In one embodiment, a method includes determining characteristics of one or more areas in an image by analyzing pixels in the image, computing a sampling density for each of the one or more areas in the image based on the characteristics of the one or more areas, generating samples corresponding to the image by sampling pixels in each of the one or more areas according to the associated sampling density, and providing the samples to a machine-learning model as an input, where the machine-learning model is configured to reconstruct the image by processing the samples.

Abstract: In one embodiment, a method includes accessing a pair of stereo images for a scene, where each image of the pair of stereo images has incomplete pixel information and k channels, stacking the pair of stereo images to form a stacked input image with 2k channels, processing the stacked input image using a machine-learning model to generate a stacked output image with 2k channels, and separating the stacked output image with 2k channels into a pair of reconstructed stereo images for the scene, where each image of the pair of reconstructed stereo images has complete pixel information and k channels.

Abstract: In various embodiments, a quality trainer trains a model that computes a value for a perceptual video quality metric for encoded video content. During a pre-training phase, the quality trainer partitions baseline values for metrics that describe baseline encoded video content into partitions based on genre. The quality trainer then performs cross-validation operations on the partitions to optimize hyperparameters associated with the model. Subsequently, during a training phase, the quality trainer performs training operations on the model that includes the optimized hyperparameters based on the baseline values for the metrics to generate a trained model. The trained model accurately tracks the video quality for the baseline encoded video content. Further, because the cross-validation operations minimize any potential overfitting, the trained model accurately and consistently predicts perceived video quality for non-baseline encoded video content across a wide range of genres.

Abstract: A method, system and computer program product for measuring non-uniformity noise produced in images or videos (e.g., infrared images or videos). Images or videos, such as infrared images or videos, are captured. A model of scene statistics (statistical model of pictures, images or videos representative of pictures, images or videos, respectively, that are captured of the physical world) is utilized to measure the non-uniformity noise in the captured images or videos by exploiting exhibited characteristics for non-uniformity noise in the captured images or videos. A number signifying a magnitude of non-uniformity for each image or video frame is then generated. In this manner, non-uniformity noise produced in images or videos is measured.

Abstract: A method, system and computer program product for classifying an image or video. An image or video to be classified is received. Scene statistics (statistical model of pictures, images or videos representative of pictures, images or videos, respectively, that are captured of the physical world) of the image or video are captured. A model (a statistical model that describes a set of probability distributions) of the image or video is then created using the captured scene statistics. A comparison between the model of the image or video with two other models of images or videos is performed, such as a model of visible light images or videos and a model of infrared images or videos. The received image or video is then classified (e.g., classified as corresponding to a visible light image) based on the comparison.

Abstract: A method, system and computer program product for measuring non-uniformity noise produced in images or videos (e.g., infrared images or videos). Images or videos, such as infrared images or videos, are captured. A model of scene statistics (statistical model of pictures, images or videos representative of pictures, images or videos, respectively, that are captured of the physical world) is utilized to measure the non-uniformity noise in the captured images or videos by exploiting exhibited characteristics for non-uniformity noise in the captured images or videos. A number signifying a magnitude of non-uniformity for each image or video frame is then generated. In this manner, non-uniformity noise produced in images or videos is measured.

Abstract: A method, system and computer program product for classifying an image or video. An image or video to be classified is received. Scene statistics (statistical model of pictures, images or videos representative of pictures, images or videos, respectively, that are captured of the physical world) of the image or video are captured. A model (a statistical model that describes a set of probability distributions) of the image or video is then created using the captured scene statistics. A comparison between the model of the image or video with two other models of images or videos is performed, such as a model of visible light images or videos and a model of infrared images or videos. The received image or video is then classified (e.g., classified as corresponding to a visible light image) based on the comparison.

Abstract: In various embodiments, a quality trainer trains a model that computes a value for a perceptual video quality metric for encoded video content. During a pre-training phase, the quality trainer partitions baseline values for metrics that describe baseline encoded video content into partitions based on genre. The quality trainer then performs cross-validation operations on the partitions to optimize hyperparameters associated with the model. Subsequently, during a training phase, the quality trainer performs training operations on the model that includes the optimized hyperparameters based on the baseline values for the metrics to generate a trained model. The trained model accurately tracks the video quality for the baseline encoded video content. Further, because the cross-validation operations minimize any potential overfitting, the trained model accurately and consistently predicts perceived video quality for non-baseline encoded video content across a wide range of genres.