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: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a sample-based video denoising software code. The hardware processor executes the sample-based video denoising software code to receive a video sequence, and select a reference frame of the video sequence to denoise. For each pixel of the reference frame, the hardware processor executes the sample-based video denoising software code to map the pixel to a sample pixel in each of other frames of the video sequence, identify a first confidence value corresponding to each of the sample pixels based on the mapping, identify a second confidence value corresponding to each of the sample pixels based on the frame that includes the sample pixel, and denoise the pixel based on a weighted combination of the sample pixels determined using the first confidence values and the second confidence values.

Abstract: A video processing system includes a computing platform having a hardware processor and a system memory storing an image cancellation software code. The hardware processor executes the image cancellation software code to receive a frame of video, detect an object image for cancellation from the received frame, and map the received frame from an original representation to a representation in which the object image does not intersect a frame boundary. The image cancellation software code also filters the mapped frame to remove features of the object image that appear to be in motion, inpaint the mapped and filtered frame to mask the object image, and reverse map the mapped and filtered frame having the object image masked to the original representation. The reverse mapped frame is composited with the received frame to produce an inpainted frame of video from which the object image has been cancelled.

Abstract: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a frame interpolation software code, the frame interpolation software code including a convolutional neural network (CNN) trained using a loss function having an image loss term summed with a phase loss term. The hardware processor executes the frame interpolation software code to receive first and second consecutive video frames including respective first and second images, and to decompose the first and second images to produce respective first and second image decompositions. The hardware processor further executes the frame interpolation software code to use the CNN to determine an intermediate image decomposition corresponding to an interpolated video frame for insertion between the first and second video frames based on the first and second image decompositions, and to synthesize the interpolated video frame based on the intermediate image decomposition.

Abstract: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a sample-based video sharpening software code. The sample-based video sharpening software code receives a video sequence, and classifies frames of the video sequence as sharp or unsharp. For each pixel of an unsharp frame, the sample-based video sharpening software code determines a mapping of the pixel to another pixel in some or all of the sharp frames, determines a reverse mapping of each of the other pixels to the pixel, identifies a first confidence value corresponding to each of the other pixels based on the mapping, identifies a second confidence value corresponding to each of the other pixels based on the mapping and the reverse mapping, and sharpens the pixel based on a weighted combination of the other pixels determined using the first and second confidence values.

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: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a frame interpolation software code, the frame interpolation software code including a convolutional neural network (CNN) trained using a loss function having an image loss term summed with a phase loss term. The hardware processor executes the frame interpolation software code to receive first and second consecutive video frames including respective first and second images, and to decompose the first and second images to produce respective first and second image decompositions. The hardware processor further executes the frame interpolation software code to use the CNN to determine an intermediate image decomposition corresponding to an interpolated video frame for insertion between the first and second video frames based on the first and second image decompositions, and to synthesize the interpolated video frame based on the intermediate image decomposition.

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: Systems and methods to generate omnistereoscopic panoramic videos are presented herein. Depth information, flow fields, and/or other information may be used to determine interpolated frame images between adjacent frame images. An omnistereoscopic panoramic video may be used in a real-world VR application.

Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.

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 rendering system includes a field-of-view detector, a display, and a computing platform including a hardware processor and a memory storing a multi-viewpoint video rendering software code. The hardware processor executes the multi-viewpoint video rendering software code to parameterize visible surfaces in a scene to define multiple texels for each visible surface, precompute one or more illumination value(s) for each texel of each visible surface, and for each texel of each visible surface, store the illumination value(s) in a cache assigned to the texel. In addition, the multi-viewpoint video rendering software code receives a perspective data from the field-of-view detector identifying one of multiple permissible perspectives for viewing the scene, and renders the scene on the display in real-time with respect to receiving the perspective data, based on the identified perspective and using one or more of the illumination value(s) precomputed for each texel of each visible surface.

Abstract: There are provided systems and methods for an interactive synchronization of multiple videos. An example system includes a memory storing a first video and a second video, the first video including first video clips and the second video including second video clips. The system further includes a processor configured to calculate a histogram based on a number of features that are similar between the first video clips and the second video clips, generate a cost matrix based on the histogram, generate a first graph that includes first nodes based on the cost matrix, compute a path through the graph using the nodes, and align the first video with the second video using the path, where the path corresponds to playback speeds for the first video and the second video.

Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.

Abstract: A video processing system includes a computing platform having a hardware processor and a system memory storing an image cancellation software code. The hardware processor executes the image cancellation software code to receive a frame of video, detect an object image for cancellation from the received frame, and map the received frame from an original representation to a representation in which the object image does not intersect a frame boundary. The image cancellation software code also filters the mapped frame to remove features of the object image that appear to be in motion, inpaint the mapped and filtered frame to mask the object image, and reverse map the mapped and filtered frame having the object image masked to the original representation. The reverse mapped frame is composited with the received frame to produce an inpainted frame of video from which the object image has been cancelled.

Abstract: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a sample-based video sharpening software code. The sample-based video sharpening software code receives a video sequence, and classifies frames of the video sequence as sharp or unsharp. For each pixel of an unsharp frame, the sample-based video sharpening software code determines a mapping of the pixel to another pixel in some or all of the sharp frames, determines a reverse mapping of each of the other pixels to the pixel, identifies a first confidence value corresponding to each of the other pixels based on the mapping, identifies a second confidence value corresponding to each of the other pixels based on the mapping and the reverse mapping, and sharpens the pixel based on a weighted combination of the other pixels determined using the first and second confidence values.

Abstract: According to one implementation, a video processing system includes a computing platform having a hardware processor and a system memory storing a sample-based video denoising software code. The hardware processor executes the sample-based video denoising software code to receive a video sequence, and select a reference frame of the video sequence to denoise. For each pixel of the reference frame, the hardware processor executes the sample-based video denoising software code to map the pixel to a sample pixel in each of other frames of the video sequence, identify a first confidence value corresponding to each of the sample pixels based on the mapping, identify a second confidence value corresponding to each of the sample pixels based on the frame that includes the sample pixel, and denoise the pixel based on a weighted combination of the sample pixels determined using the first confidence values and the second confidence values.

Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.

Abstract: Systems and methods to generate omnistereoscopic panoramic videos are presented herein. Depth information, flow fields, and/or other information may be used to determine interpolated frame images between adjacent frame images. An omnistereoscopic panoramic video may be used in a real-world VR application.

Abstract: Enhanced removing of noise and outliers from one or more point sets generated by image-based 3D reconstruction techniques is provided. In accordance with the disclosure, input images and corresponding depth maps can be used to remove pixels that are geometrically and/or photometrically inconsistent with the colored surface implied by the input images. This allows standard surface reconstruction methods (such as Poisson surface reconstruction) to perform less smoothing and thus achieve higher quality surfaces with more features. In some implementations, the enhanced point-cloud noise removal in accordance with the disclosure can include computing per-view depth maps, and detecting and removing noisy points and outliers from each per-view point cloud by checking if points are consistent with the surface implied by the other input views.