Residual vectors are compressed in a lossless compression scheme suitable for cloud DVR video content applications. Thus, a cloud DVR service provider can take many copies of the same file stored in the cloud and save storage space by compressing those copies while still maintaining their status as distinct copies, one per user. Vector quantization is used for compressing already-compressed video streams (e.g., MPEG streams). As vector quantization is a lossy compression scheme, the residual vector has to be stored to regenerate the original video stream at the decoding (playback) node. Entropy coding schemes like Arithmetic or Huffman coding can be used to compress the residual vectors. Additional strategies can be implemented to further optimize this residual compression. In some embodiments, the techniques operate to provide a 25-50% improvement in compression. Storage space is thus more efficiently used and video transmission may be faster in some cases.

Methods and compression units for compressing a two-dimensional block of image element values. The method includes: dividing the two-dimensional block of image element values into a plurality of sub-blocks of image element values; identifying which pattern of a plurality of patterns is formed by the image element values of a first sub-block of the plurality of sub-blocks; and forming a compressed block of image element values by encoding the first sub-block in the compressed block of image element values with: (i) information identifying the pattern, and (ii) the image element values of the first sub-block forming the pattern.

There is provided an information processing apparatus and a method that allow for suppression of a decrease in encoding efficiency. Correlation information is generated that results from encoding of voxel data resulting from quantization of point cloud data with use of correlation of a distribution pattern of values of the voxel data; the generated correlation information is encoded; and a bit stream including the correlation information is generated. The present disclosure is applicable to an information processing apparatus, an image processing apparatus, an electronic device, an information processing method, a program, or the like, for example.

Methods, systems, and non-transitory computer readable storage media are disclosed for reconstructing three-dimensional meshes from two-dimensional images of objects with automatic coordinate system alignment. For example, the disclosed system can generate feature vectors for a plurality of images having different views of an object. The disclosed system can process the feature vectors to generate coordinate-aligned feature vectors aligned with a coordinate system associated with an image. The disclosed system can generate a combined feature vector from the feature vectors aligned to the coordinate system. Additionally, the disclosed system can then generate a three-dimensional mesh representing the object from the combined feature vector.

An imaging method may include obtaining imaging data associated with a region of interest (ROI) of an object. The imaging data may correspond to a plurality of time-series images of the ROI. The imaging method may also include determining, based on the imaging data, a data set including a spatial basis and one or more temporal bases. The spatial basis may include spatial information of the imaging data. The one or more temporal bases may include temporal information of the imaging data. The imaging method may also include storing, in a storage medium, the spatial basis and the one or more temporal bases.

Residual vectors are compressed in a lossless compression scheme suitable for cloud DVR video content applications. Thus, a cloud DVR service provider can take many copies of the same file stored in the cloud and save storage space by compressing those copies while still maintaining their status as distinct copies, one per user. Vector quantization is used for compressing already-compressed video streams (e.g., MPEG streams). As vector quantization is a lossy compression scheme, the residual vector has to be stored to regenerate the original video stream at the decoding (playback) node. Entropy coding schemes like Arithmetic or Huffman coding can be used to compress the residual vectors. Additional strategies can be implemented to further optimize this residual compression. In some embodiments, the techniques operate to provide a 25-50% improvement in compression. Storage space is thus more efficiently used and video transmission may be faster in some cases.

Embodiments described herein provided for an instruction and associated logic to enable a processing resource including a tensor accelerator to perform optimized computation of sparse submatrix operations. One embodiment provides hardware logic to apply a numerical transform to matrix data to increase the sparsity of the data. Increasing the sparsity may result in a higher compression ratio when the matrix data is compressed.

When encoding a block of data elements in an array of data elements, the data values for data elements in the block are represented and stored in a data packet as truncated data values using a subset of one or more most significant bits of the respective bit sequences for the data values of the data elements. A rounding mode is selected from a plurality of available rounding modes that can be applied when decoding the block of data elements and an indication of the selected rounding mode is provided along with the encoded data packet. The rounding mode is associated with one or more rounding bit sequence(s) that can then be applied to the truncated data values when decoding the data packet to obtain decoded data values for the data elements in the block.

Techniques for generating a novel image using tokenized image representations are disclosed. In some embodiments, a method of generating the novel image includes generating, via a first machine learning model, a first sequence of coded representations of a first image having one or more features; generating, via a second machine learning model, a second sequence of coded representations of a sketch image having one or more edge features associated with the one or more features; predicting, via a third machine learning model, one or more subsequent coded representations based on the first sequence of coded representations and the second sequence of coded representations; and based on the subsequent coded representations, generating, via the third machine learning model, a first portion of a reconstructed image having one or more image attributes of the first image, and a second portion of the reconstructed image associated with the one or more edge features.

A three-dimensional data encoding method includes: dividing three-dimensional points included in three-dimensional data into three-dimensional point sub-clouds including a first three-dimensional point sub-cloud and a second three-dimensional point sub-cloud; appending first information indicating a space of the first three-dimensional point sub-cloud to a header of the first three-dimensional point sub-cloud, and appending second information indicating a space of the second three-dimensional point sub-cloud to a header of the second three-dimensional point sub-cloud; and encoding the first three-dimensional point sub-cloud and the second three-dimensional point sub-cloud so that the first three-dimensional point sub-cloud and the second three-dimensional point sub-cloud are decodable independently of each other.