摘要:
Methods and apparatus are provided for video encoding and decoding with learned transform and compressive sensing. An apparatus includes a video encoder for encoding an image block in a picture by determining from a training data set an adaptive transform for transforming a signal capable of representing the image block into zero coefficients and non-zero coefficients, reconstructing the image block in a pixel domain to obtain a reconstructed version of the image block by minimizing a number of the non-zero coefficients in a transform domain corresponding to the transform responsive to information of the signal and a prediction of the image block, and incorporating the reconstructed version of the image block into a coding mode that is absent from any video coding standards and video coding recommendations.
摘要:
Methods and apparatus are provided for video encoding and decoding with learned transform and compressive sensing. An apparatus includes a video encoder for encoding an image block in a picture by determining from a training data set an adaptive transform for transforming a signal capable of representing the image block into zero coefficients and non-zero coefficients, reconstructing the image block in a pixel domain to obtain a reconstructed version of the image block by minimizing a number of the non-zero coefficients in a transform domain corresponding to the transform responsive to information of the signal and a prediction of the image block, and incorporating the reconstructed version of the image block into a coding mode that is absent from any video coding standards and video coding recommendations.
摘要:
Methods and apparatus are provided for video coding and decoding with reduced bit-depth update mode and reduced chroma sampling update mode. An apparatus includes an encoder for encoding at least a portion of a picture using at least one of a reduced bit-depth update mode and a reduced chroma sampling update mode that respectively reduces at least one of a bit-depth and a chroma sampling of a residue signal corresponding to the portion.
摘要:
Methods and apparatus are provided for video coding and decoding with reduced bit-depth update mode and reduced chroma sampling update mode. An apparatus includes an encoder for encoding at least a portion of a picture using at least one of a reduced bit-depth update mode and a reduced chroma sampling update mode that respectively reduces at least one of a bit-depth and a chroma sampling of a residue signal corresponding to the portion.
摘要:
A method and apparatus are provided for detecting image blocking artifacts. The apparatus includes a full-reference blocking artifact detector for detecting blocking artifacts in a processed version of a picture based on a blockiness metric. The blockiness metric is determined based on respective local variations in the processed version of the picture and in an original version of the picture.
摘要:
A method and apparatus are provided for detecting image blocking artifacts. The apparatus includes a full-reference blocking artifact detector for detecting blocking artifacts in a processed version of a picture based on a blockiness metric. The blockiness metric is determined based on respective local variations in the processed version of the picture and in an original version of the picture.
摘要:
Methods and apparatus are provided for video image pruning. An apparatus includes a data pruner for pre-processing a picture prior to, and in preparation for, compression by encoding. The data pruner selectively removes, in the spatial domain, at least one region within the picture. At the decoder end, an apparatus includes a data restorer for receiving a decompressed picture subsequent to decompression by decoding, and post-processing the decompressed picture by selectively restoring, in the spatial domain, at least one region in the decompressed picture based on information indicating a removal of the at least one region prior to a previously performed encoding process.
摘要:
A method for processing a video sequence having a plurality of frames includes the steps of: extracting features from each of the frames, determining correspondences between the extracted features from two of the frames, estimating motion in the video sequence based on the determined correspondences, generating a background mosaic for the video sequence based on the estimated motion, and performing foreground-background segmentation on each of the frames based on the background mosaic.
摘要:
A method and apparatus are provided for reversible, polynomial based image scaling. The apparatus includes a video scaler for performing image scaling from a first base resolution image to a higher resolution image, and from the higher resolution image to a second base resolution image. The first and the second base resolution images are equal on a pixel-by-pixel basis for an entirety of the first and the second base resolution images. A scaling function used for the image scaling is based on a polynomial function having two or more degrees.
摘要:
A method for processing a video sequence having a plurality of frames includes the steps of: extracting features from each of the frames, determining correspondences between the extracted features from two of the frames, estimating motion in the video sequence based on the determined correspondences, generating a background mosaic for the video sequence based on the estimated motion, and performing foreground-background segmentation on each of the frames based on the background mosaic.