Abstract: Systems and methods are disclosed for compressing a target video. A computer-implemented method may use a computer system that include one or more physical computer processors and non-transient electronic storage. The computer-implemented method may include: obtaining the target video, extracting one or more frames from the target video, and generating an estimated optical flow based on a displacement of pixels between the one or more frames. The one or more frames may include one or more of a key frame and a target frame.

Abstract: Systems and methods for predicting a target set of pixels are disclosed. In one embodiment, a method may include obtaining target content. The target content may include a target set of pixels to be predicted. The method may also include convolving the target set of pixels to generate an estimated set of pixels. The method may include matching a second set of pixels in the target content to the target set of pixels. The second set of pixels may be within a distance from the target set of pixels. The method may include refining the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content.

Abstract: Systems and methods for predicting a target set of pixels are disclosed. In one embodiment, a method may include obtaining target content. The target content may include a target set of pixels to be predicted. The method may also include convolving the target set of pixels to generate an estimated set of pixels. The method may include matching a second set of pixels in the target content to the target set of pixels. The second set of pixels may be within a distance from the target set of pixels. The method may include refining the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content.

Abstract: One embodiment of the present invention sets forth a technique for performing deinterlacing. The technique includes separating a first interlaced video frame into a first sequence of fields ordered by time, the first sequence of fields including a first field. The technique also includes generating, by applying a deinterlacing network to a first field in the first sequence, a second field that is missing from the first sequence of fields and is complementary to the first field. The technique further includes constructing a progressive video frame based on the first field and the second field.

Abstract: A scaling application estimates a downscaling kernel used to generate a downscaled image. The scaling application upscales the downscaled image based on the estimated downscaling kernel, thereby generating a higher resolution version of the downscaled image with minimal visual artifacts. The scaling application includes various networks that perform the above operations. A kernel mapping network generates a degradation map based on the estimated downscaling kernel. A degradation-aware generator network generates a reconstructed image based on the downscaled image and the degradation map. A kernel discriminator network generates an image delta that reflects visual artifacts present in the reconstructed image. The scaling application includes a parameter optimizer that iteratively modifies the estimated downscaling kernel to reduce visual artifacts indicated in the image delta.

Abstract: A data processing system includes a computing platform having a hardware processor and a memory storing a data compression software code. The hardware processor executes the data compression software code to receive a series of compression input data and encode a first compression input data of the series to a latent space representation of the first compression input data. The data compression software code further decodes the latent space representation to produce an input space representation of the first compression input data corresponding to the latent space representation, and generates f refined latent values for re-encoding the first compression input data based on a comparison of the first compression input data with its input space representation. The data compression software code then re-encodes the first compression input data using the refined latent values to produce a first compressed data corresponding to the first compression input data.

Abstract: Systems and methods are disclosed for generating a latent space residual. A computer-implemented method may use a computer system that includes non-transient electronic storage, a graphical user interface, and one or more physical computer processors. The computer-implemented method may include: obtaining a target frame, obtaining a reconstructed frame, encoding the target frame into a latent space to generate a latent space target frame, encoding the reconstructed frame into the latent space to generate a latent space reconstructed frame, and generating a latent space residual based on the latent space target frame and the latent space reconstructed frame.

Abstract: Systems and methods are disclosed for reconstructing a frame. A computer-implemented method may use a computer system that includes non-transient electronic storage, a graphical user interface, and one or more physical computer processors. The computer-implemented method may include: obtaining one or more reference frames from non-transient electronic storage, generating one or more displacement maps based on the one or more reference frames and a target frame with the physical computer processor, generating one or more warped frames based on the one or more reference frames and the one or more displacement maps with the physical computer processor, obtaining a conditioned reconstruction model from the non-transient electronic storage, and generating one or more blending coefficients and one or more reconstructed displacement maps by applying the one or more displacement maps, the one or more warped frames, and a target frame to the conditioned reconstruction model with the physical computer processor.

Abstract: Systems and methods are disclosed for reconstructing a frame. A computer-implemented method may use a computer system that includes non-transient electronic storage, a graphical user interface, and one or more physical computer processors. The computer-implemented method may include: obtaining one or more reference frames from non-transient electronic storage, generating one or more displacement maps based on the one or more reference frames and a target frame with the physical computer processor, generating one or more warped frames based on the one or more reference frames and the one or more displacement maps with the physical computer processor, obtaining a conditioned reconstruction model from the non-transient electronic storage, and generating one or more blending coefficients and one or more reconstructed displacement maps by applying the one or more displacement maps, the one or more warped frames, and a target frame to the conditioned reconstruction model with the physical computer processor.

Abstract: Systems and methods are disclosed for generating a latent space residual. A computer-implemented method may use a computer system that includes non-transient electronic storage, a graphical user interface, and one or more physical computer processors. The computer-implemented method may include: obtaining a target frame, obtaining a reconstructed frame, encoding the target frame into a latent space to generate a latent space target frame, encoding the reconstructed frame into the latent space to generate a latent space reconstructed frame, and generating a latent space residual based on the latent space target frame and the latent space reconstructed frame.

Abstract: A scaling application estimates a downscaling kernel used to generate a downscaled image. The scaling application upscales the downscaled image based on the estimated downscaling kernel, thereby generating a higher resolution version of the downscaled image with minimal visual artifacts. The scaling application includes various networks that perform the above operations. A kernel mapping network generates a degradation map based on the estimated downscaling kernel. A degradation-aware generator network generates a reconstructed image based on the downscaled image and the degradation map. A kernel discriminator network generates an image delta that reflects visual artifacts present in the reconstructed image. The scaling application includes a parameter optimizer that iteratively modifies the estimated downscaling kernel to reduce visual artifacts indicated in the image delta.

Abstract: An image synthesis system includes a computing platform having a hardware processor and a system memory storing a software code including a neural encoder and multiple neural decoders each corresponding to a respective persona. The hardware processor executes the software code to receive target image data, and source data that identifies one of the personas, and to map the target image data to its latent space representation using the neural encoder. The software code further identifies one of the neural decoders for decoding the latent space representation of the target image data based on the persona identified by the source data, uses the identified neural decoder to decode the latent space representation of the target image data as the persona identified by the source data to produce a swapped image data, and blends the swapped image data with the target image data to produce one or more synthesized images.

Abstract: An image synthesis system includes a computing platform having a hardware processor and a system memory storing a software code including a neural encoder and multiple neural decoders each corresponding to a respective persona. The hardware processor executes the software code to receive target image data, and source data that identifies one of the personas, and to map the target image data to its latent space representation using the neural encoder. The software code further identifies one of the neural decoders for decoding the latent space representation of the target image data based on the persona identified by the source data, uses the to identified neural decoder to decode the latent space representation of the target image data as the persona identified by the source data to produce a swapped image data, and blends the swapped image data with the target image data to produce one or more synthesized images.

Abstract: A data processing system includes a computing platform having a hardware processor and a memory storing a data compression software code. The hardware processor executes the data compression software code to receive a series of compression input data and encode a first compression input data of the series to a latent space representation of the first compression input data. The data compression software code further decodes the latent space representation to produce an input space representation of the first compression input data corresponding to the latent space representation, and generates f refined latent values for re-encoding the first compression input data based on a comparison of the first compression input data with its input space representation. The data compression software code then re-encodes the first compression input data using the refined latent values to produce a first compressed data corresponding to the first compression input data.

Abstract: Systems and methods for distortion removal at multiple quality levels are disclosed. In one embodiment, a method may include receiving training content. The training content may include original content, reconstructed content, and training distortion quality levels corresponding to the reconstructed content. The reconstructed content may be derived from distorted original content. The method may also include training distortion quality levels corresponding to the reconstructed content. The method may further include receiving an initial distortion removal model. The method may include generating a conditioned distortion removal model by training the initial distortion removal model using the training content. The method may further include storing the conditioned distortion removal model.

Abstract: Systems and methods for predicting a target set of pixels are disclosed. In one embodiment, a method may include obtaining target content. The target content may include a target set of pixels to be predicted. The method may also include convolving the target set of pixels to generate an estimated set of pixels. The method may include matching a second set of pixels in the target content to the target set of pixels. The second set of pixels may be within a distance from the target set of pixels. The method may include refining the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content.

Abstract: According to one implementation, an image processing system includes a computing platform having a hardware processor and a system memory storing a software code including a convolutional neural network (CNN) trained using one or more semantic map(s). The hardware processor executes the software code to receive an original image including multiple object images each identified with one of multiple object classes, and to generate replications of the original image, each replication corresponding respectively to one of the object classes. The hardware processor further executes the software code to, for each replication, selectively modify one or more object image(s) identified with the object class corresponding to the replication, using the CNN, to produce partially modified images each corresponding respectively to an object class, and to merge the partially modified images, using the CNN, to generate a modified image corresponding to the original image.

Abstract: A video processing system includes a computing platform having a hardware processor and a memory storing a software code including a convolutional neural network (CNN). The hardware processor executes the software code to receive video data including a key video frame in color and a video sequence in gray scale, determine a first estimated colorization for each frame of the video sequence except the key video frame based on a colorization of a previous frame, and determine a second estimated colorization for each frame of the video sequence except the key video frame based on the key video frame in color. For each frame of the video sequence except the key video frame, the software code further blends the first estimated colorization with the second estimated colorization using a color fusion stage of the CNN to produce a colorized video sequence corresponding to the video sequence in gray scale.

Abstract: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a software code including an artificial neural network (ANN). The hardware processor is configured to execute the software code to receive a first video sequence having a first display resolution, and to produce a second video sequence based on the first video sequence using the ANN. The second video sequence has a second display resolution higher than the first display resolution. The ANN is configured to provide sequential frames of the second video sequence that are temporally stable and consistent in color to reduce visual flicker and color shifting in the second video sequence.

Abstract: A video processing system includes a computing platform having a hardware processor and a memory storing a software code including a convolutional neural network (CNN). The hardware processor executes the software code to receive video data including a key video frame in color and a video sequence in gray scale, determine a first estimated colorization for each frame of the video sequence except the key video frame based on a colorization of a previous frame, and determine a second estimated colorization for each frame of the video sequence except the key video frame based on the key video frame in color. For each frame of the video sequence except the key video frame, the software code further blends the first estimated colorization with the second estimated colorization using a color fusion stage of the CNN to produce a colorized video sequence corresponding to the video sequence in gray scale.