Abstract: Techniques related to distributing the video encoding processing of an input video across hardware and software systems. Such techniques include evaluating the content of the video and determine whether or the encoding operation is best to be done on the hardware system only, software system only or a hybrid hardware and software system.

Abstract: The lack of knowledge about a downstream consumer using a resized image can lead to poor inference quality of a machine learning model. Inference quality can be improved when the resizing algorithm to produce resized images closely matches the one used during training of the machine learning model. To achieve this technical task, a resizer can be made aware of downstream consumer information and apply a suitable resizing algorithm. In one scenario, the downstream consumer information is received as metadata from a downstream process. In another scenario, an optimal resizing option can be determined to maximize inference quality. In yet another scenario, a likely resizing option can be determined by assessing a filtering profile determined based on a known original image and a known resized image.

Abstract: Using a fixed group of pictures (GOP) size in video encoding significantly hinders compression efficiency due to its inability to adapt to the dynamic nature of video content. While encoding leverages spatio-temporal redundancy within a GOP for compression, a predetermined size fails to capture the varying complexity of scenes. This leads to wasted bits in low-motion segments and insufficient reference frame variation for high-motion areas, resulting in visual artifacts and reduced compression efficiency. To address this limitation, a GOP size recommendation engine involving machine learning models can determine frame-level GOP size recommendations based on pre-encoder frame statistics. The frame-level GOP size recommendations are used to adapt the GOP size for encoding video frames.

Abstract: Techniques related to distributing the video encoding processing of an input video across hardware and software systems. Such techniques include evaluating the content of the video and determine whether or the encoding operation is best to be done on the hardware system only, software system only or a hybrid hardware and software system.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed. Example apparatus disclosed herein are to process features extracted from first and second downscaled image frames to determine block classifications for respective blocks of the first and the second downscaled image frames. Disclosed example apparatus are also to generate a map based on the block classifications, the map including values representative of amounts of change associated with blocks of the second downscaled image frame and corresponding blocks of the first downscaled image frame. Disclosed example apparatus are further to adjust a quantization parameter of a full-scale image frame based on the map, the full-scale image frame corresponding to the at least one of the first or the second downscaled image frames.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed. Example apparatus disclosed herein are to process features extracted from first and second downscaled image frames to determine block classifications for respective blocks of the first and the second downscaled image frames. Disclosed example apparatus are also to generate a map based on the block classifications, the map including values representative of amounts of change associated with blocks of the second downscaled image frame and corresponding blocks of the first downscaled image frame. Disclosed example apparatus are further to adjust a quantization parameter of a full-scale image frame based on the map, the full-scale image frame corresponding to the at least one of the first or the second downscaled image frames.

Abstract: Methods, apparatuses and systems may provide for technology that quickly and accurately detects scene changes by evaluating a current frame based at least in part on a plurality of feature groups. Each of the feature groups may include a plurality of feature values determined from individual features. The individual features may include one or more spatial features of the current frame and one or more temporal features of the current frame as compared with previously evaluated temporal features of a previous reference frame. A determination of whether a scene change has occurred at the current frame may be made based at least in part on a majority vote among the plurality of feature groups.

Abstract: Methods, apparatuses and systems may provide for technology that provides adaptive Long Term Reference (LTR) frame techniques for video processing and/or coding. More particularly, implementations described herein may utilize fast content analysis based Adaptive Long Term Reference (LTR) methods and systems that can reliably decide when to turn LTR on/off, select LTR frames, and/or assign LTR frame quality for higher efficiency and higher quality encoding with practical video encoders.

Abstract: Techniques related to distributing the video encoding processing of an input video across hardware and software systems. Such techniques include evaluating the content of the video and determine whether or the encoding operation is best to be done on the hardware system only, software system only or a hybrid hardware and software system.

Abstract: Techniques related to improved video denoising using content adaptive motion compensated temporal filtering are discussed. Such techniques may include determining whether a block of a video frame is motion compensable and, when the block is motion compensable, generating a denoised block corresponding to the block using the block itself and averaged reference blocks from two or more motion compensation reference frames.

Abstract: Techniques related to content adaptive prediction distance analysis and hierarchical motion estimation for video coding may address the general problem of designing a new, advanced video codec that maximizes the achievable compression efficiency while remaining sufficiently practical for implementation on various platforms including limited devices. More specifically, certain motion estimation techniques may be adaptive to properties of the content and results in improved motion compensation, lower computational complexity, and lower cost of motion vector coding as compared to existing solutions.

Abstract: Methods, apparatuses and systems may provide for technology that quickly and accurately detects scene changes by evaluating a current frame based at least in part on a plurality of feature groups. Each of the feature groups may include a plurality of feature values determined from individual features. The individual features may include one or more spatial features of the current frame and one or more temporal features of the current frame as compared with previously evaluated temporal features of a previous reference frame. A determination of whether a scene change has occurred at the current frame may be made based at least in part on a majority vote among the plurality of feature groups.

Abstract: Methods, apparatuses and systems may provide for technology that provides adaptive Long Term Reference (LTR) frame techniques for video processing and/or coding. More particularly, implementations described herein may utilize fast content analysis based Adaptive Long Term Reference (LTR) methods and systems that can reliably decide when to turn LTR on/off, select LTR frames, and/or assign LTR frame quality for higher efficiency and higher quality encoding with practical video encoders.

Abstract: Techniques related to improved video denoising using content adaptive motion compensated temporal filtering are discussed. Such techniques may include determining whether a block of a video frame is motion compensable and, when the block is motion compensable, generating a denoised block corresponding to the block using the block itself and averaged reference blocks from two or more motion compensation reference frames.

Abstract: Techniques related to processing a mixed content video stream to generate progressive video for encoding and/or display are discussed. Such techniques may include determining conversion techniques for various portions of the mixed content video stream and converting the portions based on the determined techniques. The conversion of true interlaced video include content adaptive interlace reversal and the conversion of pseudo-interlaced telecine converted video may include adaptive telecine pattern reversal.

Abstract: Techniques related to processing a mixed content video stream to generate progressive video for encoding and/or display are discussed. Such techniques may include determining conversion techniques for various portions of the mixed content video stream and converting the portions based on the determined techniques. The conversion of true interlaced video include content adaptive interlace reversal and the conversion of pseudo-interlaced telecine converted video may include adaptive telecine pattern reversal.

Abstract: Techniques related to processing a mixed content video stream to generate progressive video for encoding and/or display are discussed. Such techniques may include determining conversion techniques for various portions of the mixed content video stream and converting the portions based on the determined techniques. The conversion of true interlaced video include content adaptive interlace reversal and the conversion of pseudo-interlaced telecine converted video may include adaptive telecine pattern reversal.

Abstract: Techniques related to processing a mixed content video stream to generate progressive video for encoding and/or display are discussed. Such techniques may include determining conversion techniques for various portions of the mixed content video stream and converting the portions based on the determined techniques. The conversion of true interlaced video include content adaptive interlace reversal and the conversion of pseudo-interlaced telecine converted video may include adaptive telecine pattern reversal.