Abstract:
Techniques related to video coding include content adaptive quantization that provides a selection between objective quality and subjective quality delta QP offsets.
Abstract:
Techniques related to coding video using adaptive quantization rounding offsets for use in transform coefficient quantization are discussed. Such techniques may include determining the value of a quantization rounding offset for a picture of a video sequence based on evaluating a maximum coding bit limit of the picture, a quantization parameter of the picture, and parameters corresponding to the video.
Abstract:
An apparatus to facilitate processing video bit stream data is disclosed. The apparatus includes one or more processors to decode occupancy map data and auxiliary patch information and generate a plurality of patch video frames based on patch data decoded from the occupancy map data and auxiliary patch information, and a memory communicatively coupled to the one or more processors.
Abstract:
Methods, apparatus, systems and articles of manufacture to adjust intra-frame encoding distortion metrics for video encoding are disclosed. Some example methods for video encoding disclosed herein include obtaining an intra-frame encoding distortion metric representative of distortion associated with a first intra-frame encoding mode for encoding a pixel block in a frame of a video sequence. Some such example methods also include adjusting the intra-frame encoding distortion metric based on a characteristic associated with the pixel block to determine an adjusted intra-frame encoding distortion metric. Some such example methods further include comparing the adjusted intra-frame encoding distortion metric with an inter-frame encoding distortion metric representative of distortion associated with a first inter-frame encoding mode for encoding the pixel block to determine whether to use at least one of the first intra-frame encoding mode or the first inter-frame encoding mode to encode the pixel block.
Abstract:
Techniques related to adaptive quantization matrix selection using machine learning for video coding are discussed. Such techniques include applying a machine learning model to generate an estimated quantization parameter for a frame and selecting a set of quantization matrices for encode of the frame from a number of sets of quantization matrices based on the estimated quantization parameter.
Abstract:
Techniques related to video coding include content adaptive quantization that provides a selection between objective quality and subjective quality delta QP offsets. An adaptive method generates an objective quality delta QP offset that achieves a best peak signal-to-noise ratio (PSNR) and/or structural similarity (SSIM) score, which refers to a similarity between images. Also, the adaptive method generates a subjective quality delta QP offset that achieves the best video multi-method assessment fusion (VMAF) score and/or multi-scale structural similarity (MSSIM) score.
Abstract:
Techniques related to adaptive quantization matrix selection using machine learning for video coding are discussed. Such techniques include applying a machine learning model to generate an estimated quantization parameter for a frame and selecting a set of quantization matrices for encode of the frame from a number of sets of quantization matrices based on the estimated quantization parameter.
Abstract:
Techniques related to coding video using adaptive quantization rounding offsets for use in transform coefficient quantization are discussed. Such techniques may include determining the value of a quantization rounding offset for a picture of a video sequence based on evaluating a maximum coding bit limit of the picture, a quantization parameter of the picture, and parameters corresponding to the video.
Abstract:
Techniques related to quantization parameter estimation for coding intra and scene change frames are discussed. Such techniques include generating features based on an intra or scene change frame including a proportion of smooth blocks and one or both of a measure of block variance and a prediction distortion, and applying a machine learning model to generate an estimated quantization parameter for encoding the intra or scene change frame.
Abstract:
Methods, apparatus, systems and articles of manufacture to perform quantization offset and/or cost factor modification for video encoding are disclosed. Some example methods for video encoding disclosed herein include adjusting a quantization offset to quantize a transform coefficient representative of a pixel block in a frame of a video sequence. For example, the quantization offset can be adjusted based on a quantization parameter obtained to quantize the transform coefficient. Some such example methods also include quantizing the transform coefficient according to the quantization parameter and the quantization offset. Some example methods for video encoding disclosed herein additionally or alternatively include adjusting a cost factor based on a characteristic of a pixel block in a frame of a video sequence. Some such example methods also include determining, based on the cost factor, a cost associated with encoding the pixel block according to a first encoding mode.